© 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
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 41471
    Prev
    Next
    INDEX
    Explanations

    Technical descriptions/specifications

    np_max-act · gemini-2.0-flash

    legal terminology related to attorney-client privilege.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron fires on language about tool maintenance or upkeep activities.

    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
    _mobile
    -0.07
    files
    -0.07
     neg
    -0.06
    ervers
    -0.06
    shopping
    -0.06
     curriculum
    -0.06
    _BACKGROUND
    -0.06
     Webster
    -0.06
     corrections
    -0.06
    /compiler
    -0.06
    POSITIVE LOGITS
    	N
    0.08
     linspace
    0.07
     canada
    0.07
    =''↵
    0.07
    _',
    0.07
    �
    0.06
    	Z
    0.06
    (padding
    0.06
    (Spring
    0.06
    (sprintf
    0.06
    Activations Density 0.127%

    No Known Activations