Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 77311
    Prev
    Next
    INDEX
    Explanations

    references to influential individuals and their accomplishments

    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
    .boost
    -0.07
    ander
    -0.07
    anders
    -0.06
    fall
    -0.06
    eric
    -0.06
    Boost
    -0.06
    agma
    -0.06
    acket
    -0.06
     læ
    -0.06
    nÃŃk
    -0.06
    POSITIVE LOGITS
     continue
    0.07
     Continue
    0.07
     also
    0.07
    also
    0.07
     even
    0.07
     truly
    0.07
     continuing
    0.07
     ayrıca
    0.07
     continued
    0.07
    agnost
    0.07
    Activations Density 0.050%

    No Known Activations