© 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. 68852
    Prev
    Next
    INDEX
    Explanations

    legal cases

    np_max-act · gemini-2.0-flash

    The neuron selectively fires on numeric tokens—especially floating‐point numbers and other in‐text numerical citations.

    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
     america
    -0.07
     clip
    -0.07
     zap
    -0.07
     devices
    -0.06
    awan
    -0.06
    _manage
    -0.06
     Winners
    -0.06
    Baby
    -0.06
    ská
    -0.06
    .feed
    -0.06
    POSITIVE LOGITS
    decess
    0.07
    tere
    0.07
    haust
    0.06
     EventArgs
    0.06
    aders
    0.06
    _UN
    0.06
     ConcurrentHashMap
    0.06
     �
    0.06
     inst
    0.06
     باع
    0.05
    Activations Density 0.028%

    No Known Activations