Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 74771
    Prev
    Next
    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash

    This neuron detects floating-point numeric scores (decimal numbers like “0.324…” or “0.543…”).

    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
     toolkit
    -0.07
     pulled
    -0.06
    HD
    -0.06
     Erotic
    -0.06
    OURS
    -0.06
     magnificent
    -0.06
    Retail
    -0.06
    chief
    -0.06
     gov
    -0.06
     Brut
    -0.06
    POSITIVE LOGITS
    .cycle
    0.07
    .ResultSet
    0.06
    [cur
    0.06
     رم
    0.06
    ,time
    0.06
    #region
    0.06
     dependable
    0.06
     сал
    0.06
    isLoading
    0.06
    .con
    0.06
    Activations Density 0.012%

    No Known Activations