© 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. 17980
    Prev
    Next
    INDEX
    Explanations

    terms related to search results and their formatting

    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
    341
    -0.07
    use
    -0.07
    oo
    -0.06
    argin
    -0.06
    ello
    -0.06
    ov
    -0.06
     eff
    -0.06
     har
    -0.06
    argo
    -0.06
    is
    -0.05
    POSITIVE LOGITS
    xmm
    0.08
    ãĥ³ãĥIJãĥ¼
    0.08
    .scalablytyped
    0.08
    mez
    0.08
    .XR
    0.08
    iens
    0.08
    Uvs
    0.08
    anlı
    0.08
    _imag
    0.08
    ãĥ³ãĤº
    0.07
    Activations Density 0.005%

    No Known Activations