© 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. 1734
    Prev
    Next
    INDEX
    Explanations

    punctuation and formatting marks

    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
    tery
    -0.06
    iê
    -0.06
    DMA
    -0.06
    ÌĤ
    -0.06
    spacer
    -0.06
    erland
    -0.06
    Bitte
    -0.05
    lech
    -0.05
     uncomp
    -0.05
    ÑĢеменно
    -0.05
    POSITIVE LOGITS
    uant
    0.08
    itr
    0.07
    abee
    0.07
    å¦
    0.07
    abe
    0.07
    essor
    0.07
    itra
    0.07
    .Compute
    0.07
    eson
    0.07
    compute
    0.07
    Activations Density 0.000%

    No Known Activations