© 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. 74138
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a continuation or building upon past achievements and successes

    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
    вид
    -0.08
    kah
    -0.07
     Leban
    -0.07
    .omg
    -0.07
    Ïħγ
    -0.07
    /Dk
    -0.07
    ovah
    -0.07
    RAIN
    -0.07
    eydi
    -0.07
    eyen
    -0.07
    POSITIVE LOGITS
     existing
    0.11
     previous
    0.10
     already
    0.09
     momentum
    0.09
     foundation
    0.09
    existing
    0.09
     Existing
    0.08
    already
    0.08
     experience
    0.08
    -existing
    0.08
    Activations Density 0.006%

    No Known Activations