© 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
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 6374
    Prev
    Next
    INDEX
    Explanations

    technical descriptions

    np_max-act · gemini-2.0-flash

    The neuron responds chiefly to passive‐voice or past‐participle verbs (e.g. “been,” “used,” “developed”).

    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
     Emer
    -0.06
     Sym
    -0.06
     BED
    -0.06
    Folder
    -0.06
    par
    -0.06
     结
    -0.06
    _after
    -0.06
     bad
    -0.06
     wann
    -0.06
     tool
    -0.06
    POSITIVE LOGITS
     convenient
    0.08
    окрем
    0.07
    argin
    0.07
     inconvenient
    0.06
    并
    0.06
    _idxs
    0.06
     доступ
    0.06
     bureaucr
    0.06
    asının
    0.06
     Partisi
    0.06
    Activations Density 0.046%

    No Known Activations