© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 14129
    Prev
    Next
    INDEX
    Explanations

    lines

    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
     grams
    -0.08
    _TH
    -0.07
    im
    -0.07
     prosper
    -0.06
     Jurassic
    -0.06
    shaw
    -0.06
     sûr
    -0.06
     comps
    -0.06
    scribe
    -0.06
    ém
    -0.06
    POSITIVE LOGITS
    =length
    0.07
     comb
    0.06
    )//
    0.06
     fict
    0.06
    يج
    0.06
    _dimension
    0.06
    ="<
    0.06
    .setdefault
    0.06
    (UINT
    0.06
     (“
    0.06
    Activations Density 0.000%

    No Known Activations