© 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. 126636
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and notations

    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
    }elseif
    -0.07
    ino
    -0.07
    unta
    -0.07
    کت
    -0.06
    åĦ¿
    -0.06
    Ngh
    -0.06
    Ùĩ
    -0.06
    MLElement
    -0.06
    -0.06
    itions
    -0.06
    POSITIVE LOGITS
    obby
    0.07
    alli
    0.06
    yan
    0.06
     Surveillance
    0.06
    umi
    0.06
    eric
    0.06
    egov
    0.06
    idebar
    0.06
    caled
    0.06
    uition
    0.06
    Activations Density 0.171%

    No Known Activations