© 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. 46519
    Prev
    Next
    INDEX
    Explanations

    sodium/salt

    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
     Jeffrey
    -0.07
     떨어
    -0.07
     apart
    -0.06
     आदम
    -0.06
     Typically
    -0.06
    しか
    -0.06
     환경
    -0.06
    .Link
    -0.06
    ुगत
    -0.06
     INTERRUPTION
    -0.06
    POSITIVE LOGITS
    Slice
    0.07
    .session
    0.06
    ned
    0.06
     ”↵
    0.06
    ated
    0.06
     --------↵
    0.06
     nivel
    0.06
    RIEND
    0.06
    .removeChild
    0.06
     cpf
    0.06
    Activations Density 0.003%

    No Known Activations