© 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. 93674
    Prev
    Next
    INDEX
    Explanations

    references to ancestry and family lineage

    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
    Ùħز
    -0.08
    amide
    -0.07
     ApiController
    -0.07
    äºŃ
    -0.07
    daq
    -0.07
    vido
    -0.07
     ÑģиÑĢ
    -0.07
    oux
    -0.07
     пÑĢиб
    -0.07
     дейÑģÑĤвиÑı
    -0.07
    POSITIVE LOGITS
     gene
    0.10
     DNA
    0.08
     branches
    0.08
     descend
    0.08
     branch
    0.08
     Gene
    0.08
    gene
    0.07
     Desc
    0.07
    DNA
    0.07
     researched
    0.07
    Activations Density 0.010%

    No Known Activations