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. 15-RESID-POST-AA
    6. 105784
    Prev
    Next
    INDEX
    Explanations

    Quotations and dialogues

    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
     waterfront
    -0.07
    adic
    -0.07
     Latinos
    -0.06
     области
    -0.06
     legit
    -0.06
    semicolon
    -0.06
    wagon
    -0.06
     nabíd
    -0.06
     Μπ
    -0.06
     下午
    -0.06
    POSITIVE LOGITS
    čení
    0.07
     ;)
    0.07
    _mount
    0.06
     Ones
    0.06
    (post
    0.06
    İS
    0.06
     hät
    0.06
    _as
    0.06
    ').↵
    0.06
    (freq
    0.06
    Activations Density 0.118%

    No Known Activations