© 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. 6853
    Prev
    Next
    INDEX
    Explanations

    other

    np_max-act · gemini-2.0-flash

    This neuron fires strongly on boilerplate cross-referencing transition phrases—e.g. “these and other advantages” or “for these and other reasons.”

    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
    -en
    -0.07
    AIR
    -0.06
    mil
    -0.06
     CGFloat
    -0.06
    ид
    -0.06
    me
    -0.06
     자유
    -0.06
     Hell
    -0.06
    air
    -0.06
    acute
    -0.06
    POSITIVE LOGITS
    abilirsiniz
    0.06
    ::<
    0.06
     bueno
    0.06
    .Debugger
    0.06
     installation
    0.06
     odpověd
    0.06
     огра
    0.06
    /goto
    0.06
    	pw
    0.06
    Authorization
    0.06
    Activations Density 0.003%

    No Known Activations