© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 56262
    Prev
    Next
    INDEX
    Explanations

    discrimination

    np_max-act · gemini-2.0-flash

    The neuron activates on terms related to statistical discrimination or classification performance (e.g. “discrimination,” “discriminant,” “diagnostic,” “classification”).

    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
    DDD
    -0.07
    .testing
    -0.06
     EX
    -0.06
    cxx
    -0.06
    QA
    -0.06
    GI
    -0.06
    XE
    -0.06
    -so
    -0.06
    ォ
    -0.06
     Subtract
    -0.06
    POSITIVE LOGITS
     Mü
    0.07
     Sty
    0.07
    ůže
    0.07
     believing
    0.06
    "])↵
    0.06
    Rules
    0.06
     graduated
    0.06
    ]),
    0.06
     město
    0.06
     nemoh
    0.06
    Activations Density 0.041%

    No Known Activations