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. 5770
    Prev
    Next
    INDEX
    Explanations

    words related to aquatic or environmental themes and their consequences

    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
    iola
    -0.08
     ÑģоÑģ
    -0.06
    eza
    -0.06
    ziej
    -0.06
     cube
    -0.06
    inite
    -0.06
    897
    -0.06
    izations
    -0.06
    hausen
    -0.06
    oplayer
    -0.06
    POSITIVE LOGITS
    /down
    0.07
    Ñħод
    0.07
    urate
    0.07
    avit
    0.06
    wards
    0.06
    लब
    0.06
    ModelError
    0.06
    adoo
    0.06
    front
    0.06
    ingly
    0.06
    Activations Density 0.001%

    No Known Activations