© 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. 61324
    Prev
    Next
    INDEX
    Explanations

    references to promotional content and news updates

    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
    /aws
    -0.07
    ãĥ³ãĤ¯
    -0.07
    bat
    -0.07
    kara
    -0.07
    ording
    -0.07
    UTF
    -0.06
     Myers
    -0.06
    anguage
    -0.06
    å¯Ł
    -0.06
    vak
    -0.06
    POSITIVE LOGITS
    ÄĽÅ¾
    0.07
    andom
    0.07
    .cgi
    0.06
    æ¥Ń
    0.06
     Lep
    0.06
     Pablo
    0.06
    avra
    0.06
    ãģĿãĤĮãģ¯
    0.06
    coni
    0.06
    .xmlbeans
    0.06
    Activations Density 0.014%

    No Known Activations