© 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. 126732
    Prev
    Next
    INDEX
    Explanations

    expressions of worry or apprehension

    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
    arella
    -0.07
    quoi
    -0.07
    ä»
    -0.07
    cca
    -0.07
    онÑĮ
    -0.07
    ukan
    -0.06
    .ToolTip
    -0.06
    ville
    -0.06
    ime
    -0.06
    ert
    -0.06
    POSITIVE LOGITS
    AY
    0.07
    ched
    0.07
    /request
    0.07
    nces
    0.06
    ìĦł
    0.06
    eck
    0.06
    ButtonModule
    0.06
    788
    0.06
    abis
    0.06
    sing
    0.06
    Activations Density 0.003%

    No Known Activations