© 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. 78257
    Prev
    Next
    INDEX
    Explanations

    comments and documentation sections within code

    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
    lou
    -0.07
    orz
    -0.07
    _FOREACH
    -0.07
    $MESS
    -0.07
    ืà¹Ī
    -0.07
    ncia
    -0.07
    urb
    -0.07
    #
    -0.07
     Wayback
    -0.06
    orr
    -0.06
    POSITIVE LOGITS
    itzer
    0.06
    ritch
    0.06
     certain
    0.06
    é¤
    0.06
    ots
    0.06
    ward
    0.06
    ery
    0.06
    -W
    0.06
     Nav
    0.06
    enberg
    0.06
    Activations Density 0.003%

    No Known Activations