© 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. 92095
    Prev
    Next
    INDEX
    Explanations

    Units of measurement

    np_max-act · gemini-2.0-flash

    The neuron flags decimal‐formatted numeric tokens (i.e. numbers with a fractional part) in measurement conversion questions.

    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
    .Elements
    -0.07
    Mon
    -0.06
     اس
    -0.06
     अभ
    -0.06
    OVE
    -0.06
     Je
    -0.06
     Sacr
    -0.06
    ίγ
    -0.06
    .after
    -0.06
     Gef
    -0.06
    POSITIVE LOGITS
     tens
    0.08
     '*
    0.07
    esti
    0.06
    paced
    0.06
    ους
    0.06
    _connections
    0.06
    하고
    0.06
     GMC
    0.06
    agi
    0.06
    歌
    0.06
    Activations Density 0.002%

    No Known Activations