© 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. 109663
    Prev
    Next
    INDEX
    Explanations

    mature

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on tokens representing decimal‐formatted numbers (i.e. numbers with a fractional “.xxx” component).

    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
    .frames
    -0.07
    ouston
    -0.07
    uges
    -0.07
    ond
    -0.07
     editors
    -0.07
    ei
    -0.07
    вал
    -0.06
    RICS
    -0.06
    test
    -0.06
    acists
    -0.06
    POSITIVE LOGITS
     assignable
    0.07
    Truthy
    0.07
     monopol
    0.06
    (strtolower
    0.06
    (photo
    0.06
     aktif
    0.06
    (月
    0.06
    ’aut
    0.06
     incorpor
    0.06
     ACPI
    0.06
    Activations Density 0.002%

    No Known Activations