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. 7-RESID-POST-AA
    6. 128746
    Prev
    Next
    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Tell
    -0.08
    chant
    -0.07
    (document
    -0.07
     BAM
    -0.07
    .Sc
    -0.07
     прож
    -0.07
    ंड
    -0.06
    bow
    -0.06
     unsus
    -0.06
    努
    -0.06
    POSITIVE LOGITS
    การส
    0.07
    olvers
    0.06
    inç
    0.06
    قع
    0.06
     GT
    0.06
    ISIS
    0.06
     riot
    0.06
     prostituerade
    0.06
    ınca
    0.06
    _an
    0.06
    Activations Density 0.040%

    No Known Activations