© 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. 106014
    Prev
    Next
    INDEX
    Explanations

    structured data or information organization elements

    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
    idos
    -0.07
    оÑĢаз
    -0.07
    izedName
    -0.07
    unos
    -0.07
    pping
    -0.07
    aption
    -0.06
    ä¹Ļ
    -0.06
     mı
    -0.06
    apus
    -0.06
    ksen
    -0.06
    POSITIVE LOGITS
    ýš
    0.07
    ụn
    0.06
    гÑĢа
    0.06
    ãĥĥãĤ«ãĥ¼
    0.06
    ieg
    0.06
    ovny
    0.06
    ateg
    0.06
     Lex
    0.06
    nice
    0.06
     Rout
    0.06
    Activations Density 0.006%

    No Known Activations