© 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. 28971
    Prev
    Next
    INDEX
    Explanations

    HTML closing tags in a document

    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
     Slut
    -0.07
    edd
    -0.06
    roke
    -0.06
    GGLE
    -0.06
    vents
    -0.06
    nap
    -0.06
    ervas
    -0.05
     Stern
    -0.05
     ((__
    -0.05
    egend
    -0.05
    POSITIVE LOGITS
    odore
    0.08
    adows
    0.07
    IGHL
    0.07
    azzi
    0.07
    ساب
    0.07
     سرÙĪ
    0.07
    \Blueprint
    0.07
    RuntimeObject
    0.07
    bsites
    0.07
    quarters
    0.06
    Activations Density 0.020%

    No Known Activations