© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 91723
    Prev
    Next
    INDEX
    Explanations

    opportunities

    np_max-act · gemini-2.0-flash

    The neuron strongly activates on words denoting “opportunities” (and their translations) or related terms about providing access to opportunities and resources.

    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
     getProduct
    -0.08
    ляют
    -0.08
     bikini
    -0.07
     nk
    -0.07
     bacteria
    -0.07
    Coverage
    -0.07
    fname
    -0.06
     getAddress
    -0.06
    .ins
    -0.06
     Liga
    -0.06
    POSITIVE LOGITS
     opportunities
    0.09
     opportunity
    0.07
    ンバ
    0.07
     deferred
    0.07
     MATRIX
    0.06
    ングル
    0.06
     toplum
    0.06
    =this
    0.06
    ifle
    0.06
    0.06
    Activations Density 0.021%

    No Known Activations