© 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 (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 92522
    Prev
    Next
    INDEX
    Explanations

    Fair

    np_max-act · gemini-2.0-flash

    This neuron detects the occurrence of the standalone token “Fair” (as in place or project names beginning with “Fair”).

    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
    <|end_of_text|>
    -0.08
     структу
    -0.08
    _stdout
    -0.07
     Nelson
    -0.07
    romatic
    -0.07
     concentrations
    -0.07
    .createTextNode
    -0.07
     systému
    -0.07
    ظة
    -0.07
    殖
    -0.07
    POSITIVE LOGITS
     fair
    0.17
     Fair
    0.16
    Fair
    0.13
     unfair
    0.11
    fair
    0.10
     fairness
    0.10
    air
    0.09
     unfairly
    0.09
     fairly
    0.08
    iff
    0.08
    Activations Density 0.009%

    No Known Activations