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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 43922
    Prev
    Next
    INDEX
    Explanations

    code punctuation

    np_max-act · gemini-2.0-flash

    It detects numeric literals containing decimal points (i.e. floating‐point numbers).

    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
     STA
    -0.07
     Swim
    -0.07
    mind
    -0.06
     Sky
    -0.06
     pineapple
    -0.06
     basis
    -0.06
     Gin
    -0.06
    owy
    -0.06
    PullParser
    -0.06
    Drivers
    -0.06
    POSITIVE LOGITS
    Trivia
    0.07
    elves
    0.06
    _RECV
    0.06
    	model
    0.06
    อำ
    0.06
     merkezi
    0.06
     vt
    0.06
     reacting
    0.06
    ourney
    0.06
    .URI
    0.06
    Activations Density 0.172%

    No Known Activations