© 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
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 55997
    Prev
    Next
    INDEX
    Explanations

    messy text/code

    np_max-act · gemini-2.0-flash

    The neuron fires on words that name or label external resources or document sections—e.g. titles, filenames, API endpoints, or linked‐resource names.

    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
    cer
    -0.06
     filme
    -0.06
     Verizon
    -0.06
    _scr
    -0.06
     розк
    -0.06
     decor
    -0.06
    IIIK
    -0.06
    rew
    -0.06
    _bal
    -0.06
    addock
    -0.06
    POSITIVE LOGITS
     Ін
    0.08
    입
    0.08
     completionHandler
    0.07
    _KEEP
    0.07
     هفته
    0.07
    Ascending
    0.07
     Дмит
    0.06
    зн
    0.06
     Called
    0.06
     είχε
    0.06
    Activations Density 0.071%

    No Known Activations