© 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
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 19395
    Prev
    Next
    INDEX
    Explanations

    PEM

    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
    historic
    -0.06
     Prosecutor
    -0.06
    na
    -0.06
    isdiction
    -0.06
    .currentUser
    -0.06
     cheeses
    -0.06
     getline
    -0.06
    ndata
    -0.06
     jurisdiction
    -0.06
    .Line
    -0.06
    POSITIVE LOGITS
    .pem
    0.10
     PEM
    0.09
     PIL
    0.07
     VLC
    0.07
     elemental
    0.06
    參
    0.06
    .Other
    0.06
    รก
    0.06
     prom
    0.06
    _family
    0.06
    Activations Density 0.001%

    No Known Activations