© 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. 109366
    Prev
    Next
    INDEX
    Explanations

    command line file paths

    np_max-act · gemini-2.0-flash

    The neuron fires on code‐block language specifiers (the tokens right after the opening triple backticks that name the language).

    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
     MK
    -0.06
    종
    -0.06
    solete
    -0.06
     tertiary
    -0.06
     �
    -0.06
    बर
    -0.06
    _bins
    -0.06
     Tarihi
    -0.06
     pantry
    -0.06
     instructor
    -0.06
    POSITIVE LOGITS
     emph
    0.07
    (dis
    0.06
     khởi
    0.06
     murderers
    0.06
     repo
    0.06
    Ін
    0.06
     uphe
    0.06
    _and
    0.06
     McInt
    0.06
     lasc
    0.06
    Activations Density 0.013%

    No Known Activations