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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 86018
    Prev
    Next
    INDEX
    Explanations

    radians

    np_max-act · gemini-2.0-flash

    This neuron does not respond to any text patterns—it stays inactive.

    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
    (lp
    -0.06
    チ
    -0.06
    (ptr
    -0.06
     hop
    -0.06
    困
    -0.06
    ITU
    -0.06
     DESC
    -0.06
    OC
    -0.06
     habitual
    -0.06
    oci
    -0.06
    POSITIVE LOGITS
    	 		
    0.07
     woodworking
    0.07
    _SelectedIndexChanged
    0.06
    _params
    0.06
     Adapter
    0.06
     Indian
    0.06
    conditional
    0.06
    _Current
    0.06
     actionTypes
    0.06
     const
    0.06
    Activations Density 0.002%

    No Known Activations