© 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. 109331
    Prev
    Next
    INDEX
    Explanations

    comparisons, relationships

    np_max-act · gemini-2.0-flash

    This neuron activates on words that describe quantitative relationships in a plotted context—especially terms like “risk,” “return,” “relationship,” “between,” and axis labels when explaining the risk–return trade-off curve.

    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
     prat
    -0.07
     chained
    -0.07
     Sparse
    -0.06
     chứa
    -0.06
    　　　　　　 　
    -0.06
     регули
    -0.06
     VAN
    -0.05
     Afterwards
    -0.05
    　 　 　 　 　 　
    -0.05
    ，被
    -0.05
    POSITIVE LOGITS
    _cmd
    0.08
    фров
    0.07
     tableLayoutPanel
    0.07
     December
    0.06
    _resolution
    0.06
     vowed
    0.06
    _rename
    0.06
     holistic
    0.06
     volum
    0.06
     ELF
    0.06
    Activations Density 0.045%

    No Known Activations