© 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. 125188
    Prev
    Next
    INDEX
    Explanations

    https

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of the HTTPS protocol (the string “https” or “HTTPS”).

    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
    _first
    -0.07
     tylko
    -0.06
    ]↵↵
    -0.06
     Scale
    -0.06
    ển
    -0.06
    cheid
    -0.06
    -set
    -0.06
    uuid
    -0.06
     frail
    -0.06
     Listings
    -0.06
    POSITIVE LOGITS
    -security
    0.07
     Savaşı
    0.07
     صنعتی
    0.06
    exus
    0.06
    intersection
    0.06
    __))
    0.06
     sonrasında
    0.06
    通過
    0.06
     защ
    0.06
     Suc
    0.06
    Activations Density 0.006%

    No Known Activations