© 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. 25334
    Prev
    Next
    INDEX
    Explanations

    guidelines

    np_max-act · gemini-2.0-flash

    The neuron activates on the repeated heading “Guidelines,” i.e. it detects occurrences of the word “Guidelines” marking those document sections.

    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
     ○
    -0.07
     nghệ
    -0.06
     존재
    -0.06
     roof
    -0.06
     epoxy
    -0.06
     आकर
    -0.06
     MainForm
    -0.06
     hasher
    -0.06
    or
    -0.06
     Packs
    -0.06
    POSITIVE LOGITS
     guidelines
    0.12
     Guidelines
    0.11
     guideline
    0.08
    ghan
    0.07
     criteria
    0.07
     Goldman
    0.07
     guidance
    0.07
    BILL
    0.07
    unkt
    0.07
    elines
    0.06
    Activations Density 0.008%

    No Known Activations