© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 124592
    Prev
    Next
    INDEX
    Explanations

    .io

    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
    +N
    -0.06
    aad
    -0.06
    Routine
    -0.06
    _altern
    -0.06
    .Values
    -0.06
     Competitive
    -0.06
    .View
    -0.06
    Vertical
    -0.06
    руб
    -0.06
     sf
    -0.06
    POSITIVE LOGITS
    (handle
    0.08
     startling
    0.06
     sensation
    0.06
     सह
    0.06
    _TypeInfo
    0.06
     parch
    0.06
    lıyor
    0.06
     процессе
    0.06
    .unpack
    0.06
    ())
    ↵
    0.06
    Activations Density 0.001%

    No Known Activations