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. 44392
    Prev
    Next
    INDEX
    Explanations

    references to specific attractions or notable experiences

    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
    sı
    -0.08
    quete
    -0.07
    e
    -0.07
    ept
    -0.07
    polator
    -0.07
    iture
    -0.06
    s
    -0.06
    ustainability
    -0.06
    PEED
    -0.06
    OUND
    -0.06
    POSITIVE LOGITS
    stone
    0.14
    ens
    0.13
    enh
    0.12
     Marian
    0.10
    hc
    0.09
    ug
    0.09
     Marion
    0.09
    estone
    0.09
    env
    0.09
    STONE
    0.08
    Activations Density 0.003%

    No Known Activations