© 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. 81150
    Prev
    Next
    INDEX
    Explanations

    XML tags that describe properties or attributes

    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
    ause
    -0.07
     bang
    -0.07
    layer
    -0.06
    divider
    -0.06
    ourke
    -0.06
     feather
    -0.06
    699
    -0.06
    ALSE
    -0.06
    787
    -0.06
    brush
    -0.06
    POSITIVE LOGITS
    è¼
    0.07
     Pey
    0.07
    raki
    0.07
    _LOGGER
    0.07
     adel
    0.07
    lasses
    0.06
    neo
    0.06
    .Bus
    0.06
    еÑĢеÑĩ
    0.06
    ingo
    0.06
    Activations Density 0.000%

    No Known Activations