Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 4492
    Prev
    Next
    INDEX
    Explanations

    /

    np_max-act · gemini-2.0-flash

    detects mentions of shell startup/profile files and modifications to the PATH environment variable.

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Record
    -0.07
    .dst
    -0.06
    ưng
    -0.06
    cellent
    -0.06
    -Cal
    -0.06
    _scalar
    -0.06
     часом
    -0.06
     :"
    -0.06
    γκ
    -0.06
    _back
    -0.06
    POSITIVE LOGITS
     ~/.
    0.12
    /.
    0.08
    cloud
    0.07
     podmínky
    0.07
    /mL
    0.07
    像是
    0.07
    uesta
    0.07
     Ein
    0.07
     azt
    0.06
    الإ
    0.06
    Activations Density 0.001%

    No Known Activations