© 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. 13068
    Prev
    Next
    INDEX
    Explanations

    file conversions

    np_max-act · gemini-2.0-flash

    code related to data conversion processes.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron detects the target output format or data type (e.g. “JSON file,” “POSIX path,” “integer,” “NumPy array,” “epoch timestamp,” “magnet URI,” etc.) in conversion-related requests.

    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
     Grace
    -0.07
     Stout
    -0.06
    -dark
    -0.06
    ，小
    -0.06
     Per
    -0.06
    mini
    -0.06
     lock
    -0.06
    Bomb
    -0.06
     relatives
    -0.06
     AH
    -0.06
    POSITIVE LOGITS
    ivr
    0.07
     많이
    0.06
    ávat
    0.06
     letz
    0.06
    аних
    0.06
     ragazzo
    0.06
    อนท
    0.06
     latina
    0.06
    .surname
    0.05
     prostě
    0.05
    Activations Density 0.053%

    No Known Activations