© 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
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 115585
    Prev
    Next
    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash

    The neuron detects the start-of-text token / document beginning marker.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    *
    -0.07
    らない
    -0.07
     необходим
    -0.06
     griev
    -0.06
    own
    -0.06
    examples
    -0.06
    ittle
    -0.06
    .PR
    -0.06
     referred
    -0.06
    preload
    -0.06
    POSITIVE LOGITS
    ("./
    0.07
    ('./
    0.07
    _typeDefinitionSize
    0.06
     dubbed
    0.06
     MethodInfo
    0.06
    /Edit
    0.06
     Traverse
    0.06
    .ObjectMeta
    0.06
    :F
    0.06
    ила
    0.06
    Activations Density 0.447%

    No Known Activations