© 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
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 15781
    Prev
    Next
    INDEX
    Explanations

    gym

    np_max-act · gemini-2.0-flash

    references to gyms, fitness centers, memberships, services, and facility/program details.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    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
     Eco
    -0.07
    integration
    -0.07
    ibel
    -0.07
     лей
    -0.06
     दर
    -0.06
     vient
    -0.06
     prosper
    -0.06
     protože
    -0.06
     Fri
    -0.06
    habi
    -0.06
    POSITIVE LOGITS
     told
    0.07
    .features
    0.07
    strlen
    0.06
    .Evaluate
    0.06
    文字
    0.06
     phòng
    0.06
     '".$_
    0.06
    TEL
    0.06
     IDS
    0.06
     bills
    0.06
    Activations Density 0.115%

    No Known Activations