© 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. 85807
    Prev
    Next
    INDEX
    Explanations

    Statistical medical research

    np_max-act · gemini-2.0-flash

    The neuron activates on decimal‐fraction tokens in measurement values (i.e. the numeric parts of floating-point data in reported results).

    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
    acak
    -0.07
     ощущ
    -0.07
    _pred
    -0.06
    .dtd
    -0.06
    shaled
    -0.06
    (!
    -0.06
    ıyla
    -0.06
     Union
    -0.06
    ACIÓN
    -0.06
     jednou
    -0.06
    POSITIVE LOGITS
     fø
    0.06
     PYTHON
    0.06
    (ob
    0.06
    沟
    0.06
    horizontal
    0.06
     Confidence
    0.06
    webpack
    0.06
     nokt
    0.06
     sporting
    0.06
    ="--
    0.06
    Activations Density 0.007%

    No Known Activations