© 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. 120280
    Prev
    Next
    INDEX
    Explanations

    problem

    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
    keyup
    -0.06
    Que
    -0.06
    وج
    -0.06
     nhựa
    -0.06
     wreck
    -0.06
    Deployment
    -0.06
     ashes
    -0.06
     brushed
    -0.06
     安
    -0.06
    -funded
    -0.06
    POSITIVE LOGITS
    했습니다
    0.07
    ỗ
    0.07
    }*
    0.06
    	So
    0.06
     pré
    0.06
    ',
↵
    0.06
     확인
    0.06
    [cnt
    0.06
    0.06
    <|begin_of_text|>
    0.06
    Activations Density 0.023%

    No Known Activations