© 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. 9-LLAMASCOPE-RES-131K
    11. 98078
    Prev
    Next
    INDEX
    Explanations

    references to sports figures and organizations

    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
    uez
    -0.06
    UNE
    -0.06
    forge
    -0.06
    anuts
    -0.06
    .opend
    -0.06
    allis
    -0.06
    icher
    -0.06
     Feld
    -0.05
    otton
    -0.05
     others
    -0.05
    POSITIVE LOGITS
    agenta
    0.08
    Ð
    0.07
    lament
    0.07
    <source
    0.07
    éĺµ
    0.06
    iteral
    0.06
    å¾ħ
    0.06
    Interop
    0.06
    اÙĦÙĦÙĩ
    0.06
    éĸ
    0.06
    Activations Density 0.109%

    No Known Activations