© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 74775
    Prev
    Next
    INDEX
    Explanations

    Conversational text

    np_max-act · gemini-2.0-flash

    The neuron strongly activates on adverbs and small transitional or discourse‐marker words (e.g. “just,” “quickly,” “here,” “in the meantime”) that link or steer the flow of a text.

    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
     rit
    -0.07
     suç
    -0.06
     dripping
    -0.06
     svých
    -0.06
    293
    -0.06
     Seen
    -0.06
    _fixture
    -0.05
    [ix
    -0.05
    등학교
    -0.05
    頭
    -0.05
    POSITIVE LOGITS
     independents
    0.08
    dül
    0.08
     зберіг
    0.07
     Throwable
    0.07
    .TEXT
    0.07
     biệt
    0.07
     BigInteger
    0.07
    -responsive
    0.07
     Propel
    0.07
    GLfloat
    0.07
    Activations Density 0.098%

    No Known Activations