© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 53385
    Prev
    Next
    INDEX
    Explanations

    asp

    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
    دار
    -0.07
     Roland
    -0.07
    起
    -0.06
    PIPE
    -0.06
    aire
    -0.06
    implicit
    -0.06
    足
    -0.06
     tor
    -0.06
     France
    -0.06
    chte
    -0.06
    POSITIVE LOGITS
     lxml
    0.10
    asterxml
    0.08
    reflection
    0.07
     disagrees
    0.07
    ethyst
    0.07
     picturesque
    0.06
     Απ
    0.06
     Esper
    0.06
    zd
    0.06
     reloading
    0.06
    Activations Density 0.001%

    No Known Activations