© 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. 25697
    Prev
    Next
    INDEX
    Explanations

    Comparisons

    np_max-act · gemini-2.0-flash

    details about chemical compounds and their interactions, particularly in pharmaceuticals and biochemical research.

    oai_token-act-pair · gpt-4o-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
    換
    -0.06
     conveyor
    -0.06
     newObj
    -0.06
     McCart
    -0.06
    >');
↵
    -0.06
    سته
    -0.06
     şeh
    -0.05
    -windows
    -0.05
     swims
    -0.05
     Vš
    -0.05
    POSITIVE LOGITS
    vekili
    0.08
     Liber
    0.08
    �재
    0.07
    -Ф
    0.07
    ười
    0.07
    onomy
    0.07
     κοι
    0.06
    endimento
    0.06
    ंज
    0.06
     Hai
    0.06
    Activations Density 0.081%

    No Known Activations