© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 27-RESID-POST-AA
    6. 99176
    Prev
    Next
    INDEX
    Explanations

    Fant

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_27/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    maze
    -0.07
    acja
    -0.06
    841
    -0.06
     Skyl
    -0.06
    uktur
    -0.06
    "time
    -0.06
    گاه
    -0.06
    _shuffle
    -0.06
     predecessors
    -0.05
    Council
    -0.05
    POSITIVE LOGITS
     그의
    0.09
     دیگران
    0.08
    ظة
    0.07
    etler
    0.07
    (integer
    0.06
    _Ent
    0.06
     التص
    0.06
     Dias
    0.06
     Fantastic
    0.06
     ic
    0.06
    Activations Density 0.001%

    No Known Activations