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. 91576
    Prev
    Next
    INDEX
    Explanations

    by

    np_max-act · gemini-2.0-flash

    This neuron detects instances of the preposition “by” introducing an agent, cause, or method.

    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
    ニニ
    -0.07
    hat
    -0.07
    идент
    -0.06
    AUT
    -0.06
    (face
    -0.06
     сви
    -0.06
    <Test
    -0.06
    _sheet
    -0.06
     Hakk
    -0.06
     инт
    -0.06
    POSITIVE LOGITS
     by
    0.08
    }$
    0.07
    .Col
    0.07
     WCS
    0.06
     Boris
    0.06
    .Perform
    0.06
     pořad
    0.06
    ději
    0.06
     obsessed
    0.06
    arl
    0.06
    Activations Density 0.030%

    No Known Activations