© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 6756
    Prev
    Next
    INDEX
    Explanations

    .txt

    np_max-act · gemini-2.0-flash

    The neuron responds to occurrences of “.txt” (e.g. license file names with a .txt extension).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    골
    -0.06
    -primary
    -0.06
    och
    -0.06
    Benef
    -0.06
    ิน
    -0.06
    Ping
    -0.06
    ule
    -0.06
    customers
    -0.05
    _ISO
    -0.05
    917
    -0.05
    POSITIVE LOGITS
     federally
    0.07
     τις
    0.07
    _DESTROY
    0.07
     guarding
    0.07
     Τι
    0.06
     engineers
    0.06
    vertising
    0.06
    (marker
    0.06
     filenames
    0.06
     technician
    0.06
    Activations Density 0.000%

    No Known Activations