© 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. 8857
    Prev
    Next
    INDEX
    Explanations

    Dates and URLs

    np_max-act · gemini-2.0-flash

    The neuron specializes in spotting URL and web‐resource path fragments (e.g. “.com,” “/wp-content,” “/uploads,” file extensions like “.png”/“.jpg”).

    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
    _position
    -0.08
    anco
    -0.07
     rear
    -0.07
     aficion
    -0.07
     ホ
    -0.06
     lith
    -0.06
     stones
    -0.06
    _DMA
    -0.06
    _sentence
    -0.06
    !!
    -0.06
    POSITIVE LOGITS
     паци
    0.07
    _lineno
    0.07
    "';
    0.07
     Чтобы
    0.07
    いつ
    0.07
    cents
    0.06
    'name
    0.06
     заболевания
    0.06
    ốc
    0.06
    clamation
    0.06
    Activations Density 0.005%

    No Known Activations