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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 58073
    Prev
    Next
    INDEX
    Explanations

    common structural words

    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
     ern
    -0.06
     shredd
    -0.06
     ix
    -0.06
    enan
    -0.06
     silently
    -0.06
     precip
    -0.06
     kut
    -0.06
    鲁
    -0.06
     pests
    -0.06
    .output
    -0.06
    POSITIVE LOGITS
    년에
    0.07
    NSBundle
    0.07
     устройства
    0.07
     Αρχ
    0.07
    ).'</
    0.06
    Internet
    0.06
     Expedition
    0.06
    acağız
    0.06
     Воз
    0.06
    iд
    0.06
    Activations Density 0.245%

    No Known Activations