© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 126956
    Prev
    Next
    INDEX
    Explanations

    references to timeframes and upcoming events

    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
     tut
    -0.07
    rouch
    -0.07
    berger
    -0.06
    arms
    -0.05
    åł´
    -0.05
    ç½²
    -0.05
     often
    -0.05
    apel
    -0.05
    OfString
    -0.05
    ords
    -0.05
    POSITIVE LOGITS
     actionTypes
    0.07
    /DTD
    0.07
    ignum
    0.07
    >NN
    0.07
    /WebAPI
    0.07
    üstü
    0.06
    êu
    0.06
    .www
    0.06
     Cres
    0.06
     according
    0.06
    Activations Density 0.015%

    No Known Activations