© 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. 55837
    Prev
    Next
    INDEX
    Explanations

    expressions reflecting uncertainty or mixed feelings

    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
    ik
    -0.06
    ube
    -0.06
     Garcia
    -0.06
     s
    -0.06
    ead
    -0.05
     now
    -0.05
    _
    -0.05
    åIJĪ
    -0.05
    amp
    -0.05
     sq
    -0.05
    POSITIVE LOGITS
    SupportedContent
    0.08
    NewProp
    0.07
    illisecond
    0.07
    avana
    0.07
    GuidId
    0.07
    isser
    0.07
     onDataChange
    0.07
    SGlobal
    0.07
    utr
    0.07
    reno
    0.07
    Activations Density 0.032%

    No Known Activations