© 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. 94799
    Prev
    Next
    INDEX
    Explanations

    numerical data and statistical references

    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
    onga
    -0.07
    aira
    -0.06
    izio
    -0.06
    asser
    -0.06
    vice
    -0.06
    ong
    -0.06
    Deposit
    -0.06
    062
    -0.05
     overl
    -0.05
    alis
    -0.05
    POSITIVE LOGITS
    DED
    0.07
    ednou
    0.07
    .IsAny
    0.07
    ulton
    0.06
    edes
    0.06
    Ïīνα
    0.06
    ursors
    0.06
    Ĥæķ°
    0.06
    ied
    0.06
    iesz
    0.06
    Activations Density 0.008%

    No Known Activations