© 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. 3-RESID-POST-AA
    11. 95342
    Prev
    Next
    INDEX
    Explanations

    ive

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cer
    -0.06
     defenses
    -0.06
    [\
    -0.06
    (operator
    -0.06
     signatures
    -0.06
     characterized
    -0.06
    _minus
    -0.06
     determination
    -0.06
    available
    -0.06
     poles
    -0.06
    POSITIVE LOGITS
    ive
    0.10
    IVE
    0.07
    тив
    0.07
    otive
    0.07
    ώντας
    0.06
    alive
    0.06
    _fre
    0.06
     título
    0.06
     계약
    0.06
     haircut
    0.06
    Activations Density 0.001%

    No Known Activations