© 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. 28159
    Prev
    Next
    INDEX
    Explanations

    references to specific years and significant events related to those years

    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
    nÃŃ
    -0.08
    ordo
    -0.07
    олом
    -0.07
    ephir
    -0.07
    ách
    -0.07
    enuous
    -0.07
    VERRIDE
    -0.07
    æīį
    -0.07
    hr
    -0.07
    око
    -0.07
    POSITIVE LOGITS
    ìĦł
    0.07
    âĢ³
    0.06
    pendicular
    0.06
    woke
    0.06
    teen
    0.06
    нез
    0.06
    WD
    0.06
    uder
    0.06
    hof
    0.06
    âĢ²
    0.06
    Activations Density 0.054%

    No Known Activations