© 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. 78141
    Prev
    Next
    INDEX
    Explanations

    references to multimedia components and precise route paths in programming

    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
    تÙĥ
    -0.07
     Provid
    -0.07
    ynom
    -0.07
    reeting
    -0.07
    oub
    -0.07
    phan
    -0.07
    ordes
    -0.07
    dyby
    -0.07
    važ
    -0.07
    bsites
    -0.07
    POSITIVE LOGITS
    =true
    0.10
    ä¸Ķ
    0.09
    ness
    0.07
    =True
    0.07
    =false
    0.06
     Forces
    0.06
    NESS
    0.06
     mission
    0.06
    =yes
    0.06
     Keller
    0.06
    Activations Density 0.017%

    No Known Activations