© 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 EvalsExportsAPI 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. 3597
    Prev
    Next
    INDEX
    Explanations

    statements describing the nature or characteristics of films

    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
     gre
    -0.06
    ething
    -0.06
    785
    -0.06
    -www
    -0.06
     integral
    -0.06
    acz
    -0.05
     recurrent
    -0.05
     bý
    -0.05
     uncomment
    -0.05
     Crossing
    -0.05
    POSITIVE LOGITS
    indr
    0.10
    azi
    0.08
    ÙĨز
    0.08
    ç´Ģ
    0.08
    ritt
    0.07
    pons
    0.07
    alles
    0.07
    oldem
    0.07
    CHAIN
    0.07
    ensitive
    0.07
    Activations Density 0.019%

    No Known Activations