© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 41080
    Prev
    Next
    INDEX
    Explanations

    job appointments

    np_max-act · gemini-2.0-flash

    specific references to basketball seasons, teams, and coaching events.

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

    The neuron activates on tokens naming organizational roles or titles (e.g. head coach, director, vice chairman).

    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
    .timezone
    -0.06
     metric
    -0.06
     millenn
    -0.06
    erm
    -0.06
     первую
    -0.06
    .mockito
    -0.06
    ानव
    -0.06
    eut
    -0.06
     стоит
    -0.06
     какой
    -0.05
    POSITIVE LOGITS
     Relation
    0.07
    Obsolete
    0.06
    มห
    0.06
     errorThrown
    0.06
     طبي
    0.06
    .icons
    0.06
     sebeb
    0.06
    =p
    0.06
    /md
    0.06
     estim
    0.06
    Activations Density 0.056%

    No Known Activations