© 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. 42734
    Prev
    Next
    INDEX
    Explanations

    code, configuration files

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of specific byte‐field names and positions (e.g. “message ID,” “data length,” “checksum,” etc.) in a fixed‐length data frame specification.

    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
     windy
    -0.07
     critics
    -0.07
     insol
    -0.06
    portrait
    -0.06
    dictionary
    -0.06
    elsing
    -0.06
    �
    -0.06
    RP
    -0.06
    _short
    -0.06
    スペ
    -0.06
    POSITIVE LOGITS
    	InputStream
    0.07
     objev
    0.06
     vatandaş
    0.06
    asking
    0.06
     ego
    0.06
     Encyclopedia
    0.06
     painfully
    0.06
    plementary
    0.06
     důležité
    0.06
     Genetic
    0.06
    Activations Density 0.158%

    No Known Activations