Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 92719
    Prev
    Next
    INDEX
    Explanations

    document descriptions

    np_max-act · gemini-2.0-flash

    This neuron primarily detects section or subsection headings (e.g. titles like “Dependencies,” “Our Goal,” “Installing SoftHSM,” etc.).

    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
    -compatible
    -0.07
    мещ
    -0.07
     gere
    -0.07
     converge
    -0.06
     pipeline
    -0.06
    λη
    -0.06
     migration
    -0.06
    ,the
    -0.06
    ène
    -0.06
     campaign
    -0.06
    POSITIVE LOGITS
    ////////////////////////////////////////////////////////////////////////////////
    0.07
    @login
    0.07
     mysl
    0.06
    UUID
    0.06
    -thirds
    0.06
     Mathf
    0.06
    Buttons
    0.06
     Counsel
    0.06
     Might
    0.06
    /********************************
    0.06
    Activations Density 0.097%

    No Known Activations