© 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. 126464
    Prev
    Next
    INDEX
    Explanations

    instructional content and practical guidance

    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
    unami
    -0.07
    unting
    -0.07
    AtPath
    -0.06
    ifax
    -0.06
     Permanent
    -0.06
    ICES
    -0.06
    roup
    -0.06
     Correction
    -0.06
    _nat
    -0.06
     repeat
    -0.06
    POSITIVE LOGITS
     article
    0.07
    .scalablytyped
    0.07
    usercontent
    0.07
    atomic
    0.06
     reluct
    0.06
     ÙħÙĤاÙĦÙĩ
    0.06
     scrolled
    0.06
    cul
    0.06
    obil
    0.06
     information
    0.06
    Activations Density 0.017%

    No Known Activations