© 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
    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. 91715
    Prev
    Next
    INDEX
    Explanations

    glass

    np_max-act · gemini-2.0-flash

    The neuron detects common container-based idiomatic or metaphorical expressions (like “forest for the trees,” “putting all your eggs in one basket,” “half the glass empty/full,” or “pouring new wine into old bottles”).

    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
    'b
    -0.08
     temporary
    -0.07
     leader
    -0.06
     announce
    -0.06
    pent
    -0.06
    plib
    -0.06
     로
    -0.06
     negotiate
    -0.06
     aren
    -0.06
    .join
    -0.06
    POSITIVE LOGITS
    .Future
    0.07
     verv
    0.07
    horn
    0.06
    DataService
    0.06
    の一
    0.06
    .fillStyle
    0.06
     Phonetic
    0.06
     manière
    0.06
     Analytics
    0.06
    _gp
    0.06
    Activations Density 0.030%

    No Known Activations