Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 43910
    Prev
    Next
    INDEX
    Explanations

    lack of research

    np_max-act · gemini-2.0-flash

    The neuron detects language signaling a lack or scarcity of prior studies or evidence (e.g. “paucity,” “few,” “no ... studies”).

    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
    licht
    -0.06
    descriptor
    -0.06
     appointment
    -0.06
    sequence
    -0.06
    cookie
    -0.06
    白
    -0.06
     penetrating
    -0.06
     deux
    -0.06
     conscience
    -0.06
    	xml
    -0.06
    POSITIVE LOGITS
     Produkte
    0.07
     비밀
    0.07
     dedim
    0.06
    <Tag
    0.06
    .xlim
    0.06
     �
    0.06
     EventType
    0.06
    .chapter
    0.06
    _fs
    0.06
     Formatter
    0.06
    Activations Density 0.031%

    No Known Activations