© 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. 19-RESID-POST-AA
    6. 87694
    Prev
    Next
    INDEX
    Explanations

    Med

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -kit
    -0.08
    орож
    -0.07
    irting
    -0.07
    etailed
    -0.07
     WN
    -0.07
    rine
    -0.07
    τζ
    -0.06
    WEEN
    -0.06
     bee
    -0.06
     tongue
    -0.06
    POSITIVE LOGITS
     deepcopy
    0.07
    (nameof
    0.07
    (localStorage
    0.06
     strerror
    0.06
     moż
    0.06
    しても
    0.06
    homes
    0.06
    FXML
    0.06
     повинен
    0.06
    .execSQL
    0.06
    Activations Density 0.008%

    No Known Activations