© 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. 5438
    Prev
    Next
    INDEX
    Explanations

    DSM

    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
     اطلاعات
    -0.06
     مض
    -0.06
     берез
    -0.06
    attr
    -0.06
     solicitud
    -0.06
    ecurity
    -0.06
     mart
    -0.06
    ulle
    -0.06
    �
    -0.05
    ━
    -0.05
    POSITIVE LOGITS
     DSM
    0.11
    (user
    0.07
     LoginComponent
    0.07
     والم
    0.07
    >'
↵
    0.07
    SM
    0.07
     神
    0.07
    )"↵↵
    0.07
     rám
    0.06
     onDataChange
    0.06
    Activations Density 0.001%

    No Known Activations