© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 106611
    Prev
    Next
    INDEX
    Explanations

    statements that assert or emphasize the existence or importance of a subject

    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
    zin
    -0.08
    acid
    -0.07
    esi
    -0.06
    ead
    -0.06
    hiba
    -0.06
     dig
    -0.06
    etest
    -0.06
    amon
    -0.06
    zik
    -0.06
    _fwd
    -0.06
    POSITIVE LOGITS
     toward
    0.09
     towards
    0.09
     tw
    0.07
    ırak
    0.07
    onus
    0.06
    igli
    0.06
    .tw
    0.06
    оÑĢов
    0.06
    ä¹İ
    0.06
     how
    0.06
    Activations Density 0.008%

    No Known Activations