© 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. 105347
    Prev
    Next
    INDEX
    Explanations

    references to competitive achievements and performance outcomes

    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
    ucha
    -0.06
    hend
    -0.06
    lope
    -0.06
    orf
    -0.06
     Hou
    -0.06
     æĮ
    -0.06
     cast
    -0.05
    ByEmail
    -0.05
     ÐłÐ°
    -0.05
    족
    -0.05
    POSITIVE LOGITS
     natives
    0.07
    cznie
    0.07
    immer
    0.07
    ãĥ¼ãĤ
    0.07
     fond
    0.07
     personally
    0.06
     annually
    0.06
    ë§Īëĭ¤
    0.06
    ÙĪÙĦÛĮ
    0.06
    endor
    0.06
    Activations Density 0.014%

    No Known Activations