© 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. 119090
    Prev
    Next
    INDEX
    Explanations

    phrases related to motivation and self-improvement

    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
    /from
    -0.08
    è¢ĭ
    -0.07
    ods
    -0.07
    sein
    -0.07
    acific
    -0.06
    iyon
    -0.06
    /TR
    -0.06
    ADOS
    -0.06
    nr
    -0.06
    aho
    -0.06
    POSITIVE LOGITS
     boundaries
    0.10
     limits
    0.09
     Limits
    0.09
     pushed
    0.08
     pushing
    0.08
     aside
    0.08
     envelopes
    0.08
     envelope
    0.08
     кноп
    0.08
     buttons
    0.08
    Activations Density 0.010%

    No Known Activations