© 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. 94112
    Prev
    Next
    INDEX
    Explanations

    the presence of numerical data and references in text

    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
    chts
    -0.08
    arer
    -0.07
    _reporting
    -0.06
    lets
    -0.06
    illez
    -0.06
    ná
    -0.06
    leases
    -0.06
     desn
    -0.06
    Ú¾
    -0.06
     dÆ°Æ¡ng
    -0.06
    POSITIVE LOGITS
     case
    0.09
     implications
    0.08
     lessons
    0.08
    case
    0.08
     example
    0.08
    åħ¼
    0.07
    ights
    0.07
     comparison
    0.07
     towards
    0.07
     caso
    0.07
    Activations Density 0.021%

    No Known Activations