© 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. 12692
    Prev
    Next
    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash

    instances of specific dates and references to events or announcements related to them.

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

    The neuron detects the “Archive for” heading that marks the start of archive or category sections.

    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
     Though
    -0.07
    seniz
    -0.07
     confiscated
    -0.07
    onz
    -0.06
    adi
    -0.06
    hone
    -0.06
     },
↵
↵
    -0.06
    的问题
    -0.06
     pathMatch
    -0.06
     blending
    -0.06
    POSITIVE LOGITS
     cane
    0.07
    心里
    0.07
     heavens
    0.06
    .getSelectionModel
    0.06
     бол
    0.06
     JMenuItem
    0.06
     ply
    0.06
     fulfilled
    0.06
    .getSelectedItem
    0.06
     путем
    0.06
    Activations Density 0.000%

    No Known Activations