© 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. 15-LLAMASCOPE-RES-131K
    11. 27018
    Prev
    Next
    INDEX
    Explanations

    terms related to achievement and success

    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
    aking
    -0.08
    aks
    -0.07
    efined
    -0.07
    ascript
    -0.07
    /of
    -0.07
    /OR
    -0.07
    adium
    -0.06
    ìį¨
    -0.06
    /email
    -0.06
    nim
    -0.06
    POSITIVE LOGITS
     goals
    0.08
    ieve
    0.07
     accomplished
    0.07
     goal
    0.07
    ment
    0.07
    uter
    0.07
     accomplish
    0.07
    yonel
    0.07
     consensus
    0.07
    ácil
    0.06
    Activations Density 0.019%

    No Known Activations