© 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. 55427
    Prev
    Next
    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash

    The neuron strongly activates on programming‐language code tokens and syntax (e.g. code fences, keywords, language names), i.e. it detects code snippets.

    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
     bgColor
    -0.07
     Sender
    -0.06
     inquire
    -0.06
    Fonts
    -0.06
    .rabbit
    -0.06
    _required
    -0.06
     patient
    -0.06
    Developer
    -0.06
    compileComponents
    -0.06
    'image
    -0.06
    POSITIVE LOGITS
    %p
    0.07
    zeń
    0.06
     od
    0.06
     Möglich
    0.06
     %.
    0.06
    �
    0.06
     -.
    0.06
     Develop
    0.06
    くだ
    0.06
     Provided
    0.06
    Activations Density 0.021%

    No Known Activations