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. 3-RESID-POST-AA
    6. 122003
    Prev
    Next
    INDEX
    Explanations

    keyboards

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    exit
    -0.07
    umbling
    -0.07
     districts
    -0.07
     bh
    -0.06
    ("../
    -0.06
    >$
    -0.06
     dropdown
    -0.06
    >
    -0.06
     fractions
    -0.06
    anal
    -0.06
    POSITIVE LOGITS
     keyboards
    0.13
    Keyboard
    0.09
     Keyboard
    0.09
    .Keyboard
    0.07
    _keyboard
    0.07
    UNCTION
    0.07
    keyboard
    0.07
     Rhode
    0.06
     glBegin
    0.06
     EDGE
    0.06
    Activations Density 0.002%

    No Known Activations