© 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. 15363
    Prev
    Next
    INDEX
    Explanations

    references to specific locations or directions

    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
    //{{
    -0.10
    resco
    -0.07
     wound
    -0.07
    orgot
    -0.07
    åīĽ
    -0.07
    illez
    -0.07
    enberg
    -0.06
    baru
    -0.06
    ETY
    -0.06
    æĹıèĩªæ²»
    -0.06
    POSITIVE LOGITS
    survey
    0.06
     Void
    0.06
    rosse
    0.06
    ugal
    0.06
    ãĥ³ãĥī
    0.06
     tanım
    0.05
    -mark
    0.05
     Alabama
    0.05
    Survey
    0.05
     land
    0.05
    Activations Density 0.000%

    No Known Activations