© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 43530
    Prev
    Next
    INDEX
    Explanations

    uncertainty/possibility

    np_max-act · gemini-2.0-flash

    medical conditions that involve complications and their treatment options.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron detects hedging or speculative language—words and phrases that signal uncertainty or project future outcomes (e.g. may, might, perhaps, will, seems).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    kud
    -0.06
     thuật
    -0.06
    Layers
    -0.06
     mesh
    -0.06
     sciences
    -0.06
    皮
    -0.06
    .eng
    -0.06
    Format
    -0.06
     convinc
    -0.06
     feedback
    -0.05
    POSITIVE LOGITS
     �
    0.07
    <Location
    0.07
    :NSLocalizedString
    0.07
    .iteritems
    0.07
    UniformLocation
    0.07
     чемпіон
    0.07
    (descriptor
    0.07
     알려
    0.06
    _DURATION
    0.06
     СССР
    0.06
    Activations Density 0.103%

    No Known Activations