Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 5538
    Prev
    Next
    INDEX
    Explanations

    technical references and error messages related to software development

    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
    _FOREACH
    -0.08
    ieu
    -0.07
    άβ
    -0.07
    enis
    -0.07
    ascus
    -0.07
    ecal
    -0.07
    бо
    -0.07
    Ïĩη
    -0.07
    enu
    -0.06
    ouch
    -0.06
    POSITIVE LOGITS
    ilver
    0.06
    dex
    0.06
    .native
    0.06
    ordes
    0.06
     Uz
    0.06
     Breitbart
    0.05
     Dal
    0.05
    ç¥ĸ
    0.05
    astically
    0.05
    ¦
    0.05
    Activations Density 0.000%

    No Known Activations