© 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. 73665
    Prev
    Next
    INDEX
    Explanations

    information related to eBook downloads and links

    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
     Jennings
    -0.06
    enna
    -0.06
    ãĥĥ
    -0.06
    dek
    -0.06
     Het
    -0.06
    izard
    -0.06
     Tradable
    -0.06
    omon
    -0.06
    ocos
    -0.06
    ">ÃĹ</
    -0.05
    POSITIVE LOGITS
    سÙĩ
    0.07
     ob
    0.07
    ãĥ¼ãĥĢ
    0.07
    eron
    0.06
     reve
    0.06
     rit
    0.06
    orgot
    0.06
    ddit
    0.06
    -null
    0.06
    eleri
    0.06
    Activations Density 0.004%

    No Known Activations