© 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. 38845
    Prev
    Next
    INDEX
    Explanations

    references to ceramic and porcelain materials

    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
    ing
    -0.08
    OrCreate
    -0.07
    884
    -0.07
    곡
    -0.07
    414
    -0.07
    434
    -0.06
    tu
    -0.06
    eko
    -0.06
    <?↵
    -0.06
    sert
    -0.06
    POSITIVE LOGITS
    rete
    0.09
    ÙĪرات
    0.08
    /pl
    0.08
    ized
    0.08
    ause
    0.07
    -animation
    0.07
    .pretty
    0.07
    arrera
    0.07
    ован
    0.07
    ahlen
    0.07
    Activations Density 0.006%

    No Known Activations