© 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. 128737
    Prev
    Next
    INDEX
    Explanations

    terms related to academic writing and essays

    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
    ourke
    -0.06
     Karlov
    -0.06
    otta
    -0.06
    elian
    -0.06
    ầy
    -0.06
     Cord
    -0.06
    lias
    -0.06
    _href
    -0.06
    uada
    -0.06
    ncmp
    -0.06
    POSITIVE LOGITS
    idar
    0.08
    ervices
    0.07
    ervice
    0.07
     services
    0.07
    $o
    0.06
     professionals
    0.06
    ĩ
    0.06
    oven
    0.06
     Professionals
    0.06
     hire
    0.06
    Activations Density 0.003%

    No Known Activations