© 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. 25331
    Prev
    Next
    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash

    The neuron fires on mentions of historical institutional transitions—especially the station’s absorption into or privatization of the railway network.

    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
     Brent
    -0.06
    ConfigureAwait
    -0.06
    /Library
    -0.06
    कर
    -0.06
    ук
    -0.05
     للد
    -0.05
    -focus
    -0.05
    али
    -0.05
    fout
    -0.05
     Muk
    -0.05
    POSITIVE LOGITS
    getti
    0.08
    も
    0.07
     aggregate
    0.07
    _category
    0.07
     therapies
    0.07
    .component
    0.07
     sebeb
    0.06
     _('
    0.06
    -contained
    0.06
    therapy
    0.06
    Activations Density 0.024%

    No Known Activations