© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 1431
    Prev
    Next
    INDEX
    Explanations

    ./

    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
     JSONObject
    -0.08
    298
    -0.06
    tracks
    -0.06
    .isBlank
    -0.06
    29
    -0.06
    parity
    -0.06
    27
    -0.06
    ırlar
    -0.06
    02
    -0.06
     zoo
    -0.06
    POSITIVE LOGITS
    =./
    0.08
     "./
    0.08
    pf
    0.08
     Guru
    0.08
    /config
    0.08
    ("./
    0.07
    档
    0.07
     Bộ
    0.07
     корп
    0.07
    Bộ
    0.07
    Activations Density 0.004%

    No Known Activations