© 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. 28721
    Prev
    Next
    INDEX
    Explanations

    conversational elements and expressions of uncertainty or inquiry

    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
    ram
    -0.07
    æĥ
    -0.07
    enberg
    -0.07
    indle
    -0.06
    .ml
    -0.06
    ance
    -0.06
    habi
    -0.06
    $p
    -0.06
    義
    -0.06
    imi
    -0.06
    POSITIVE LOGITS
     um
    0.08
     mean
    0.08
    .um
    0.07
    taÅŁ
    0.07
    otas
    0.07
    ystate
    0.07
     uh
    0.07
    026
    0.06
    umm
    0.06
    Um
    0.06
    Activations Density 0.103%

    No Known Activations