© 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 (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 92543
    Prev
    Next
    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash

    The neuron fires on the boilerplate phrase “distributed in the hope that it will be useful” in GPL‐style license headers.

    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
    Running
    -0.07
    -running
    -0.07
    Spider
    -0.06
    χαν
    -0.06
    LTR
    -0.06
    /random
    -0.06
    .party
    -0.06
    probe
    -0.06
    .ONE
    -0.06
    .network
    -0.06
    POSITIVE LOGITS
    に見
    0.07
     İl
    0.07
     τι
    0.07
     ры
    0.07
    DefaultCloseOperation
    0.07
     می
    0.07
     navigation
    0.06
     connection
    0.06
     doğ
    0.06
     Nicholas
    0.06
    Activations Density 0.001%

    No Known Activations