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. 91847
    Prev
    Next
    INDEX
    Explanations

    *)

    np_max-act · gemini-2.0-flash

    The neuron detects regular‐expression syntax (e.g. the “^”, “(.*)”, and “$” tokens) in htaccess RewriteRule/RewriteCond lines.

    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
    ست
    -0.07
     Poster
    -0.07
     Budd
    -0.06
     CHIP
    -0.06
     populated
    -0.06
     تی
    -0.06
     इन
    -0.06
     WEEK
    -0.06
    цію
    -0.06
    ila
    -0.06
    POSITIVE LOGITS
    _SCHEMA
    0.06
    		 
    0.06
    ))->
    0.06
     consideration
    0.06
     \(
    0.06
    	assert
    0.06
    ]=$
    0.06
    .MediaType
    0.06
     '-')
    0.06
     createUser
    0.06
    Activations Density 0.001%

    No Known Activations