© 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. 93468
    Prev
    Next
    INDEX
    Explanations

    elements related to decision-making and comparison within a context

    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
    rung
    -0.08
    leurs
    -0.07
    ัà¸Ļà¹Ħà¸Ķ
    -0.07
    æĹıèĩªæ²»
    -0.07
    nty
    -0.07
    âĶģ
    -0.07
    unge
    -0.07
    CSI
    -0.07
    eldom
    -0.07
    sse
    -0.07
    POSITIVE LOGITS
     options
    0.10
     various
    0.10
     several
    0.09
    options
    0.08
     alternatives
    0.08
    Options
    0.08
     possibilities
    0.08
     Options
    0.08
    _options
    0.07
    .options
    0.07
    Activations Density 0.023%

    No Known Activations