© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 74684
    Prev
    Next
    INDEX
    Explanations

    terms related to bibliographic and registration information in academic contexts

    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
    arez
    -0.07
    tember
    -0.06
     Cash
    -0.06
    åĿĽ
    -0.06
    icap
    -0.06
    iability
    -0.06
    oras
    -0.06
    incy
    -0.06
    gili
    -0.06
    olest
    -0.06
    POSITIVE LOGITS
    aza
    0.07
    Ìĥ
    0.07
     prostitut
    0.07
    argout
    0.07
    LAB
    0.07
    \Annotation
    0.06
     hạng
    0.06
     mrb
    0.06
    ephir
    0.06
    pis
    0.06
    Activations Density 0.001%

    No Known Activations