© 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. 87305
    Prev
    Next
    INDEX
    Explanations

    terms related to scientific experiments and cellular biology

    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
     Tow
    -0.07
    ainer
    -0.07
    older
    -0.06
     nett
    -0.06
     trades
    -0.06
     heck
    -0.06
     nuisance
    -0.06
    som
    -0.06
     Huntington
    -0.06
    ==>
    -0.05
    POSITIVE LOGITS
    DDS
    0.07
    itura
    0.07
     Kup
    0.07
    άκ
    0.07
    enty
    0.07
    bian
    0.06
     Hait
    0.06
     hete
    0.06
    .qq
    0.06
    ÑĨÑİ
    0.06
    Activations Density 0.043%

    No Known Activations