© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 13581
    Prev
    Next
    INDEX
    Explanations

    Academic papers

    np_max-act · gemini-2.0-flash

    This neuron activates on the names or acronyms of technical methods and algorithms (e.g., AdaBoost, RANSAC, Velvet, MOND).

    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
    UIS
    -0.07
     předpok
    -0.06
    Fs
    -0.06
     incoming
    -0.06
    getMessage
    -0.06
     archetype
    -0.06
    cons
    -0.06
     XML
    -0.06
    にも
    -0.06
     Tibetan
    -0.06
    POSITIVE LOGITS
    ...↵↵↵↵
    0.08
    .inline
    0.06
    ]↵↵↵
    0.06
     уси
    0.06
     písem
    0.06
     سلس
    0.06
    яви
    0.06
     kuvvet
    0.06
    ahaha
    0.06
    忍
    0.06
    Activations Density 0.166%

    No Known Activations