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. 69073
    Prev
    Next
    INDEX
    Explanations

    bath

    np_max-act · gemini-2.0-flash

    The neuron primarily detects occurrences of the character sequence “bath” (e.g. in “bath,” “bathing,” “bathyscaphe,” etc.).

    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
     ragazza
    -0.07
    team
    -0.07
    Exec
    -0.07
     commonly
    -0.07
     statements
    -0.07
    REL
    -0.07
     emitted
    -0.06
    sharp
    -0.06
     elected
    -0.06
    賢
    -0.06
    POSITIVE LOGITS
     bath
    0.15
     Bath
    0.14
     baths
    0.11
    ath
    0.08
     Baths
    0.08
     bathing
    0.07
     bathtub
    0.07
    lh
    0.07
     Braves
    0.07
     シ
    0.07
    Activations Density 0.005%

    No Known Activations