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. 31-LLAMASCOPE-RES-131K
    6. 11431
    Prev
    Next
    INDEX
    Explanations

    phrases related to educational opportunities and data science

    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
    487
    -0.07
     libertin
    -0.07
    layui
    -0.07
    384
    -0.06
    rase
    -0.06
    _BOTH
    -0.06
    ydro
    -0.06
    lichkeit
    -0.06
    AVE
    -0.06
     dna
    -0.06
    POSITIVE LOGITS
     administrations
    0.07
    centre
    0.06
    auge
    0.06
    anje
    0.06
    nad
    0.06
    iken
    0.06
    uv
    0.06
     Amid
    0.06
    esch
    0.06
    eto
    0.06
    Activations Density 0.029%

    No Known Activations