© 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. 29579
    Prev
    Next
    INDEX
    Explanations

    expressions related to personal growth 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
    iren
    -0.08
    viso
    -0.07
    esti
    -0.07
    avenport
    -0.07
    uja
    -0.07
    ismet
    -0.07
    _EXTERN
    -0.07
    prec
    -0.06
    ottie
    -0.06
    ÙĬار
    -0.06
    POSITIVE LOGITS
     ongoing
    0.13
     continuing
    0.11
     continuously
    0.11
     constantly
    0.11
    ongo
    0.11
     continue
    0.11
     continues
    0.10
     continual
    0.10
     continuous
    0.10
     continually
    0.10
    Activations Density 0.061%

    No Known Activations