© 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. 11-RESID-POST-AA
    11. 25671
    Prev
    Next
    INDEX
    Explanations

    icus

    np_max-act · gemini-2.0-flash

    legal terminology and citations related to court cases.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     المغرب
    -0.06
    .radians
    -0.06
     standout
    -0.06
    .gwt
    -0.06
    ("{
    -0.05
    ]initWith
    -0.05
    .label
    -0.05
    .expand
    -0.05
    epend
    -0.05
     ott
    -0.05
    POSITIVE LOGITS
    ρισ
    0.08
    isky
    0.08
    /K
    0.07
    лерг
    0.07
    ierz
    0.07
    ước
    0.07
     Driving
    0.07
     Beaver
    0.07
     Đức
    0.06
    rax
    0.06
    Activations Density 0.000%

    No Known Activations