© 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. 81094
    Prev
    Next
    INDEX
    Explanations

    colons indicating items or lists

    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
    002
    -0.06
    eg
    -0.06
    lf
    -0.06
    595
    -0.06
    legg
    -0.06
     dop
    -0.06
    ek
    -0.06
     Buckingham
    -0.06
    491
    -0.06
    pix
    -0.06
    POSITIVE LOGITS
    opal
    0.07
    EMU
    0.06
    .onView
    0.06
    vise
    0.06
    _CLUSTER
    0.06
    nave
    0.06
    ãģĹãģ®
    0.06
    ãĥĨãĥ«
    0.06
    dust
    0.06
    ê°ij
    0.06
    Activations Density 0.000%

    No Known Activations