© 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. 77092
    Prev
    Next
    INDEX
    Explanations

    verbs that indicate motivation or efforts to propel actions or results

    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
     Finch
    -0.07
    cai
    -0.07
    kB
    -0.07
    sw
    -0.06
    opher
    -0.06
    isd
    -0.06
    dir
    -0.06
    avras
    -0.06
    sl
    -0.06
    _sl
    -0.06
    POSITIVE LOGITS
     wed
    0.10
     wedge
    0.08
    haft
    0.08
     drove
    0.08
    ToFront
    0.08
     toward
    0.07
    atto
    0.07
    .drive
    0.07
    away
    0.07
    ToEnd
    0.07
    Activations Density 0.013%

    No Known Activations