© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 94314
    Prev
    Next
    INDEX
    Explanations

    technical terms and notations related to mathematical frameworks and equations

    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
    lÃŃ
    -0.07
     Bien
    -0.06
     gest
    -0.06
     continuum
    -0.06
     rein
    -0.06
    roadcast
    -0.06
    @show
    -0.06
     firm
    -0.06
     Gran
    -0.06
     jer
    -0.06
    POSITIVE LOGITS
    -spin
    0.07
     Magnus
    0.07
     spins
    0.07
     bord
    0.07
    Spin
    0.07
    spin
    0.07
    .spin
    0.07
    ázd
    0.07
     Spin
    0.07
     ElementType
    0.06
    Activations Density 0.007%

    No Known Activations