© 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. 5016
    Prev
    Next
    INDEX
    Explanations

    references to reviews or evaluations

    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
    eza
    -0.08
    enuity
    -0.07
    fahren
    -0.07
    æĤŁ
    -0.07
    duk
    -0.07
    edback
    -0.07
    kle
    -0.07
    celik
    -0.07
    itura
    -0.07
    kening
    -0.07
    POSITIVE LOGITS
    ÑģÑĮ
    0.07
    usk
    0.06
     Dict
    0.06
     hol
    0.06
    ariant
    0.06
    att
    0.06
    uth
    0.06
    ym
    0.06
    iesen
    0.06
    \Domain
    0.05
    Activations Density 0.000%

    No Known Activations