© 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. 129095
    Prev
    Next
    INDEX
    Explanations

    headers related to API requests specifying JSON content

    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
    ugin
    -0.08
    bote
    -0.08
    SWG
    -0.08
    eyse
    -0.07
    asu
    -0.07
    omain
    -0.07
    imity
    -0.07
    regor
    -0.07
    redi
    -0.07
    umbn
    -0.07
    POSITIVE LOGITS
     accept
    0.07
    ;q
    0.07
     Accept
    0.07
     Gecko
    0.07
    Accept
    0.06
     prefer
    0.06
     prefers
    0.06
     Glass
    0.06
     Schneider
    0.06
    CEE
    0.05
    Activations Density 0.001%

    No Known Activations