© 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. 54939
    Prev
    Next
    INDEX
    Explanations

    references to automated systems and their effectiveness

    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
     bis
    -0.08
     Bis
    -0.07
    lesi
    -0.07
    elez
    -0.07
    ural
    -0.06
    -fetch
    -0.06
    ely
    -0.06
     palindrome
    -0.06
    otron
    -0.06
    affen
    -0.06
    POSITIVE LOGITS
     novelty
    0.07
    noise
    0.07
     eventual
    0.07
    Permanent
    0.07
    _transient
    0.07
    fad
    0.07
     sooner
    0.07
    å¾Ĵ
    0.07
     subs
    0.07
    tiv
    0.07
    Activations Density 0.035%

    No Known Activations