© 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. 7-RESID-POST-AA
    11. 25136
    Prev
    Next
    INDEX
    Explanations

    ethics in study participation

    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
    autop
    -0.06
    ]){↵
    -0.06
    Ông
    -0.06
    fwrite
    -0.06
     Libraries
    -0.06
     });
↵
↵
    -0.06
    >}↵
    -0.06
     ));↵
    -0.06
    归
    -0.06
     Audience
    -0.06
    POSITIVE LOGITS
    ckså
    0.07
     seiz
    0.06
     нак
    0.06
     واج
    0.06
    рол
    0.06
    enerate
    0.06
    foobar
    0.06
    appropri
    0.06
    scores
    0.06
     الأمريكي
    0.06
    Activations Density 0.187%

    No Known Activations