© 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. 16581
    Prev
    Next
    INDEX
    Explanations

    references to scientific articles and databases

    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
     Sunder
    -0.07
    anim
    -0.07
    аков
    -0.07
    ays
    -0.07
     anim
    -0.07
    dae
    -0.06
    ÙģصÙĦ
    -0.06
    .Compile
    -0.06
    udur
    -0.06
    ipment
    -0.06
    POSITIVE LOGITS
     free
    0.08
    ecz
    0.07
    free
    0.06
     libre
    0.06
     gratis
    0.06
    PMC
    0.06
     FREE
    0.06
    tics
    0.06
    _fre
    0.06
     Truy
    0.06
    Activations Density 0.002%

    No Known Activations