© 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. 8918
    Prev
    Next
    INDEX
    Explanations

    type

    np_max-act · gemini-2.0-flash

    This neuron fires on parameter‐assignment lines in configuration sections, specifically on the “type = …” settings.

    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
    startsWith
    -0.07
     reminis
    -0.06
     Pok
    -0.06
     Natur
    -0.06
     В
    -0.06
    eve
    -0.06
     Zhao
    -0.06
     sensual
    -0.06
     nn
    -0.06
    /y
    -0.06
    POSITIVE LOGITS
    )-(
    0.06
    CFG
    0.06
     getPage
    0.06
     Enumerable
    0.06
    -share
    0.06
    oriasis
    0.06
     Citation
    0.06
    .scalar
    0.06
    ixo
    0.06
     denote
    0.06
    Activations Density 0.010%

    No Known Activations