© 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. 18530
    Prev
    Next
    INDEX
    Explanations

    Citations/References

    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
    /message
    -0.07
     hockey
    -0.06
    Dialog
    -0.06
     qualifier
    -0.06
    -util
    -0.06
    них
    -0.06
    menu
    -0.06
    ony
    -0.06
     Rally
    -0.06
    _album
    -0.06
    POSITIVE LOGITS
    (Vec
    0.07
     })
    0.06
     розп
    0.06
     interpre
    0.06
     наслід
    0.06
    namespace
    0.06
     consequ
    0.06
    (Response
    0.06
    ARE
    0.06
    arbonate
    0.06
    Activations Density 0.147%

    No Known Activations