© 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. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 3822
    Prev
    Next
    INDEX
    Explanations

    actions related to progressing or advancing in a physical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çu
    -0.07
    rary
    -0.07
    IBUTES
    -0.06
    輯
    -0.06
    ebe
    -0.06
    DEST
    -0.06
    lum
    -0.06
    VC
    -0.06
    wn
    -0.06
    ompiler
    -0.06
    POSITIVE LOGITS
    okers
    0.06
    elo
    0.06
    ersen
    0.06
    ëŀĮ
    0.06
    uzzi
    0.06
    ós
    0.06
     Henderson
    0.05
    ihad
    0.05
    ABA
    0.05
    oker
    0.05
    Activations Density 0.000%

    No Known Activations