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. 15-RESID-POST-AA
    6. 25134
    Prev
    Next
    INDEX
    Explanations

    text snippets

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     retreated
    -0.07
     penis
    -0.07
     awakeFromNib
    -0.06
    torrent
    -0.06
    _that
    -0.06
    igmoid
    -0.06
    .getActivity
    -0.06
     Ville
    -0.06
     findAll
    -0.06
    ίνει
    -0.06
    POSITIVE LOGITS
     Tier
    0.07
     PATH
    0.06
    urred
    0.06
     saturn
    0.06
     Sanders
    0.06
    (KeyCode
    0.06
    anvas
    0.06
    EOF
    0.06
    _connections
    0.06
     YES
    0.06
    Activations Density 0.142%

    No Known Activations