© 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. 3349
    Prev
    Next
    INDEX
    Explanations

    terms related to scientific classification and nomenclature

    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
    /tos
    -0.07
    gart
    -0.06
     Colt
    -0.06
    853
    -0.06
    ket
    -0.06
    /inet
    -0.06
    ulet
    -0.06
     aver
    -0.06
    elier
    -0.06
    lane
    -0.06
    POSITIVE LOGITS
    pag
    0.07
    assis
    0.07
     Ung
    0.07
    auc
    0.07
     Species
    0.07
    ádu
    0.07
    benh
    0.06
    allback
    0.06
    stag
    0.06
     αξ
    0.06
    Activations Density 0.005%

    No Known Activations