© 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. 75582
    Prev
    Next
    INDEX
    Explanations

    index

    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
    utom
    -0.06
     pode
    -0.06
    _nums
    -0.06
    ebek
    -0.06
    Props
    -0.06
    рич
    -0.06
    >[
    -0.06
    PRINT
    -0.06
    CAT
    -0.06
    roups
    -0.06
    POSITIVE LOGITS
     джер
    0.07
     introduce
    0.07
     sketch
    0.06
     감사
    0.06
     Interview
    0.06
    UserCode
    0.06
    !↵↵↵↵
    0.06
    ▋
    0.06
     scrambling
    0.06
    -lg
    0.06
    Activations Density 0.018%

    No Known Activations