© 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 EvalsExportsinterp-engineNEWAPI 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. 92363
    Prev
    Next
    INDEX
    Explanations

    references to official entities and roles related to governance and security

    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
    lio
    -0.07
    ehr
    -0.07
    555
    -0.07
    uch
    -0.06
    acos
    -0.06
    ecast
    -0.06
    æĿ
    -0.06
    ãĤĤãģ®
    -0.06
    .rev
    -0.06
    ://%
    -0.06
    POSITIVE LOGITS
     says
    0.07
    rych
    0.07
    :
    0.07
    æĽ°
    0.07
    locator
    0.06
     terk
    0.06
    rane
    0.06
    unda
    0.06
     said
    0.06
    quier
    0.06
    Activations Density 0.021%

    No Known Activations