Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 103875
    Prev
    Next
    INDEX
    Explanations

    scientific research

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    (request
    -0.08
     warehouse
    -0.07
     attachment
    -0.06
    -chart
    -0.06
    	options
    -0.06
    .after
    -0.06
     arte
    -0.06
    urations
    -0.06
    _.
    -0.06
    *
    -0.06
    POSITIVE LOGITS
     dequeueReusableCellWithIdentifier
    0.07
     बत
    0.07
    igmoid
    0.06
    ntp
    0.06
    �
    0.06
     kéo
    0.06
    огу
    0.06
     notoriously
    0.06
    teborg
    0.06
     रख
    0.06
    Activations Density 0.030%

    No Known Activations