© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 126921
    Prev
    Next
    INDEX
    Explanations

    references to specific datasets or research entities

    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
    ypse
    -0.07
    idlo
    -0.07
    erver
    -0.07
    ýš
    -0.07
    kke
    -0.07
    alnız
    -0.07
    .HTTP
    -0.07
    éru
    -0.07
    erce
    -0.07
    yc
    -0.06
    POSITIVE LOGITS
    prech
    0.06
    ÑĤÑĢо
    0.06
    éĤ¦
    0.06
    WER
    0.06
     regards
    0.06
     Wich
    0.06
     WCHAR
    0.06
    CAD
    0.06
     Reaper
    0.06
    itched
    0.05
    Activations Density 0.029%

    No Known Activations