© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 92638
    Prev
    Next
    INDEX
    Explanations

    conjunctions and separators

    np_max-act · gemini-2.0-flash

    The neuron activates on verbs (particularly action words like German “abfragen,” “erstellt,” “gelöst,” “ändern” and English CRUD verbs such as “create,” “read,” “update,” “delete”).

    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
     debugging
    -0.07
     bailout
    -0.06
    _number
    -0.06
     Sun
    -0.06
    =config
    -0.06
    정부
    -0.06
     kings
    -0.06
    595
    -0.06
     LIGHT
    -0.06
    Slug
    -0.06
    POSITIVE LOGITS
    색
    0.07
     Gson
    0.06
    ارد
    0.06
     reckless
    0.06
    flt
    0.06
    ể
    0.06
    getCell
    0.06
     Os
    0.06
    	TokenNameIdentifier
    0.06
     alanda
    0.06
    Activations Density 0.047%

    No Known Activations