© 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. 15-LLAMASCOPE-RES-131K
    11. 88355
    Prev
    Next
    INDEX
    Explanations

    references to submission requirements and instructions

    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
    ildo
    -0.07
     xÆ°Æ¡ng
    -0.07
    terra
    -0.07
    .mk
    -0.07
    mania
    -0.07
    ndern
    -0.07
    _tooltip
    -0.06
    shima
    -0.06
    -tooltip
    -0.06
    vince
    -0.06
    POSITIVE LOGITS
     allowed
    0.09
    allowed
    0.08
     offered
    0.08
     Allowed
    0.07
    _allowed
    0.07
     Offer
    0.07
     opportunity
    0.07
    ASK
    0.06
    791
    0.06
     available
    0.06
    Activations Density 0.071%

    No Known Activations