© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 54085
    Prev
    Next
    INDEX
    Explanations

    Intensifiers

    np_max-act · gemini-2.0-flash

    The neuron fires on intensifying adverbs and adjectives (e.g. “very,” “extremely,” “horrific,” “absolutely”) that signal heightened emphasis or strong feeling.

    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
     Henderson
    -0.07
    Clean
    -0.07
     Marvin
    -0.07
     Increasing
    -0.07
     Jacob
    -0.06
    Boston
    -0.06
    .Tensor
    -0.06
    行动
    -0.06
     inflicted
    -0.06
     ringing
    -0.06
    POSITIVE LOGITS
     postup
    0.07
     variable
    0.06
    .chars
    0.06
     useHistory
    0.06
    timestamps
    0.06
    &w
    0.06
    �
    0.06
    خل
    0.06
    lev
    0.06
     Inf
    0.06
    Activations Density 0.072%

    No Known Activations