© 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. 62709
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to data access and querying

    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
    emble
    -0.08
    ellij
    -0.07
    loys
    -0.07
    orks
    -0.07
    pra
    -0.06
    itol
    -0.06
    ccione
    -0.06
    eyim
    -0.06
    ork
    -0.06
    ÙĨب
    -0.06
    POSITIVE LOGITS
    325
    0.06
    liš
    0.06
    .scalablytyped
    0.06
    ignet
    0.05
     heel
    0.05
    ãĥ¼ãĥĹ
    0.05
    ImageData
    0.05
     smashed
    0.05
     ho
    0.05
    Ø´ÙĬ
    0.05
    Activations Density 0.009%

    No Known Activations