© 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. 15-RESID-POST-AA
    11. 124630
    Prev
    Next
    INDEX
    Explanations

    "the only way is up"

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -month
    -0.07
     arrange
    -0.06
     troubles
    -0.06
    .real
    -0.06
    法律
    -0.06
     alright
    -0.06
    (port
    -0.06
     buffalo
    -0.06
    scal
    -0.06
     Omar
    -0.06
    POSITIVE LOGITS
     StObject
    0.07
    oso
    0.06
    icles
    0.06
    ANGER
    0.06
    plash
    0.06
     teng
    0.06
    UX
    0.06
    =_("
    0.06
     getActivity
    0.06
    .CONFIG
    0.06
    Activations Density 0.062%

    No Known Activations