© 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 EvalsExportsAPI 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. 125711
    Prev
    Next
    INDEX
    Explanations

    references to television episode details and recaps

    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
    vron
    -0.07
    ĩ
    -0.07
    .oc
    -0.06
    abad
    -0.06
    imulation
    -0.06
    ayo
    -0.06
    amba
    -0.06
    alan
    -0.06
    ieber
    -0.06
    ·»
    -0.06
    POSITIVE LOGITS
     titled
    0.08
    igure
    0.08
    uento
    0.07
    called
    0.07
    terdam
    0.07
    uitka
    0.07
    åı«
    0.07
    icha
    0.06
    loth
    0.06
     called
    0.06
    Activations Density 0.004%

    No Known Activations