© 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. 56245
    Prev
    Next
    INDEX
    Explanations

    call

    np_max-act · gemini-2.0-flash

    This neuron detects placeholder naming phrases like “let’s call it…” (i.e. occurrences of “let’s/we’ll call it”).

    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
    垂
    -0.07
    爸
    -0.07
    �
    -0.06
     je
    -0.06
    �
    -0.06
    аніт
    -0.06
    qe
    -0.06
    토
    -0.06
    BufferData
    -0.06
    uş
    -0.06
    POSITIVE LOGITS
     Khal
    0.06
    participant
    0.06
     filmes
    0.06
    _TOKEN
    0.06
    IBE
    0.06
    (an
    0.06
     abbrev
    0.06
    national
    0.06
     assay
    0.06
    _mesh
    0.06
    Activations Density 0.011%

    No Known Activations