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. 91078
    Prev
    Next
    INDEX
    Explanations

    ="

    np_max-act · gemini-2.0-flash

    The neuron spotlights occurrences of HTML “title=” attributes (i.e. the attribute name and its quoted value).

    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
     specified
    -0.06
    новаж
    -0.06
    Separator
    -0.06
     pragmatic
    -0.06
    rijk
    -0.06
    EMPLARY
    -0.06
    	script
    -0.06
     Sized
    -0.06
     illustrated
    -0.05
    ++
    -0.05
    POSITIVE LOGITS
     fallback
    0.07
     Centro
    0.07
    OLUME
    0.06
     outweigh
    0.06
     went
    0.06
    �
    0.06
     ¿
    0.06
    MethodManager
    0.06
    .ask
    0.06
    liğinde
    0.06
    Activations Density 0.001%

    No Known Activations