© 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. 35308
    Prev
    Next
    INDEX
    Explanations

    forums web

    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_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
     işe
    -0.07
     다음과
    -0.06
     pdu
    -0.06
    -Co
    -0.06
    iets
    -0.06
     ناحیه
    -0.06
    ireccion
    -0.06
    >).
    -0.06
    ítica
    -0.06
     pisc
    -0.06
    POSITIVE LOGITS
     Plus
    0.07
    (np
    0.07
    Latitude
    0.07
     Mash
    0.07
     np
    0.06
    EMBER
    0.06
     Apr
    0.06
    dateFormat
    0.06
    RestController
    0.06
    .experimental
    0.06
    Activations Density 0.019%

    No Known Activations