© 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. 119146
    Prev
    Next
    INDEX
    Explanations

    technical terms related to settings and configuration in software or programming contexts

    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
    owers
    -0.07
    ież
    -0.06
     Cald
    -0.06
    ede
    -0.06
    -describedby
    -0.06
    uxt
    -0.06
     lesb
    -0.06
     Latter
    -0.06
    entlich
    -0.06
    emm
    -0.06
    POSITIVE LOGITS
    (++
    0.07
    Impl
    0.06
    å®Ŀ
    0.06
     DropIndex
    0.06
    fal
    0.06
     Elias
    0.06
    .createFrom
    0.06
    isha
    0.06
    ttl
    0.05
    shire
    0.05
    Activations Density 0.007%

    No Known Activations