© 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. 92569
    Prev
    Next
    INDEX
    Explanations

    past actions

    np_max-act · gemini-2.0-flash

    The neuron is primarily detecting floating-point numeric literals (decimal numbers).

    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
    mpeg
    -0.08
     geographic
    -0.07
     mates
    -0.07
    _quest
    -0.07
     strategic
    -0.07
     Rap
    -0.07
    (factor
    -0.07
    ژن
    -0.06
    стория
    -0.06
     Human
    -0.06
    POSITIVE LOGITS
     rằng
    0.06
    や
    0.06
     routed
    0.06
     대구
    0.06
    _descriptor
    0.06
     issuance
    0.06
    _gp
    0.05
    �
    0.05
    (())↵
    0.05
     После
    0.05
    Activations Density 0.023%

    No Known Activations