© 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. 34138
    Prev
    Next
    INDEX
    Explanations

    showed/shown

    np_max-act · gemini-2.0-flash

    scientific terms related to receptors and cell signaling processes.

    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
     dors
    -0.06
     Exc
    -0.06
     эту
    -0.06
     Aj
    -0.06
     �
    -0.06
     Onc
    -0.06
     Vis
    -0.06
     amb
    -0.06
     Cav
    -0.06
     debounce
    -0.06
    POSITIVE LOGITS
    //!↵
    0.08
     Winner
    0.06
    .ToolStripSeparator
    0.06
    تغ
    0.06
    (_)
    0.06
     ку
    0.06
    -a
    0.06
    .Question
    0.06
    äs
    0.06
    асти
    0.06
    Activations Density 0.026%

    No Known Activations