© 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. 15-RESID-POST-AA
    6. 62674
    Prev
    Next
    INDEX
    Explanations

    lama cha

    np_max-act · gemini-2.0-flash

    mentions of the model name "LLaMA" (and close token variants like La, MA, llama).

    oai_token-act-pair · gpt-5-miniTriggered by @yooniel31
    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
    PROFILE
    -0.07
    adders
    -0.06
    inders
    -0.06
     NOTHING
    -0.06
    .life
    -0.06
     craz
    -0.06
     boiling
    -0.06
    ?}",
    -0.06
     afraid
    -0.06
    TOOLS
    -0.06
    POSITIVE LOGITS
     quản
    0.07
     여행
    0.06
    fill
    0.06
     peers
    0.06
     Franç
    0.06
    立て
    0.06
    irthday
    0.06
    ORMAL
    0.06
    (Direction
    0.06
     estable
    0.06
    Activations Density 0.005%

    No Known Activations