© 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. 15-LLAMASCOPE-RES-131K
    11. 948
    Prev
    Next
    INDEX
    Explanations

    concepts relating to recycling and sustainable practices

    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
    ifacts
    -0.07
    atore
    -0.07
    onec
    -0.07
    ima
    -0.07
     Bard
    -0.06
    edla
    -0.06
    rax
    -0.06
    xAC
    -0.06
    емÑĥ
    -0.06
     па
    -0.06
    POSITIVE LOGITS
     Ty
    0.07
     component
    0.06
    opis
    0.06
    _components
    0.06
     dig
    0.06
    dig
    0.06
     Hir
    0.06
    Ty
    0.06
    uent
    0.06
    ä»ĭ
    0.06
    Activations Density 0.003%

    No Known Activations