© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 1450
    Prev
    Next
    INDEX
    Explanations

    details about archaeological discoveries and their preservation status

    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
     Fet
    -0.06
    qus
    -0.06
    Frozen
    -0.06
     CU
    -0.06
     Heroes
    -0.06
    esz
    -0.06
    zim
    -0.06
    567
    -0.06
    ernational
    -0.06
    867
    -0.06
    POSITIVE LOGITS
     lost
    0.08
     Gone
    0.08
     gone
    0.08
     perish
    0.08
     losses
    0.07
    gone
    0.07
    loss
    0.07
    LOSS
    0.07
     original
    0.07
     originals
    0.07
    Activations Density 0.024%

    No Known Activations