© 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. 128832
    Prev
    Next
    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash

    The neuron fires on words and phrases that signal interpretation or inference of results (e.g. “indicating,” “suggesting,” “is required,” “is correlated”).

    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
     براى
    -0.07
     Extremely
    -0.07
     hypothetical
    -0.06
     assures
    -0.06
    .iterator
    -0.06
     previous
    -0.06
     predominantly
    -0.06
     pourrait
    -0.06
     favourable
    -0.06
     intend
    -0.06
    POSITIVE LOGITS
    مي
    0.08
    .makeText
    0.06
    .actor
    0.06
    OutOfRangeException
    0.06
    ταν
    0.06
     Spice
    0.06
     vegas
    0.06
    .');
    0.06
    사진
    0.06
     screened
    0.06
    Activations Density 0.103%

    No Known Activations