© 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. 27616
    Prev
    Next
    INDEX
    Explanations

    references to music tracks and songs

    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
    roud
    -0.06
    uu
    -0.06
    elta
    -0.06
    มา
    -0.06
    opens
    -0.06
     subclass
    -0.06
     cr
    -0.05
    -sama
    -0.05
     ted
    -0.05
    Aspect
    -0.05
    POSITIVE LOGITS
    à¹ģรà¸ģ
    0.09
    orde
    0.09
    onth
    0.08
    entes
    0.08
    åıİ
    0.07
    363
    0.07
    PerPage
    0.07
    afort
    0.07
    zas
    0.07
    wizard
    0.07
    Activations Density 0.017%

    No Known Activations