© 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. 80825
    Prev
    Next
    INDEX
    Explanations

    of

    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
     села
    -0.07
     recurrent
    -0.07
     centroid
    -0.07
     graphene
    -0.07
     wcs
    -0.06
     видно
    -0.06
    альної
    -0.06
     здійсню
    -0.06
    47
    -0.06
     toolbar
    -0.06
    POSITIVE LOGITS
    .management
    0.07
    AMED
    0.07
    *(
    0.06
     různ
    0.06
    าว
    0.06
    غم
    0.06
     numberWithInt
    0.06
     lorsque
    0.06
    ETYPE
    0.06
    ания
    0.06
    Activations Density 0.075%

    No Known Activations