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. 44371
    Prev
    Next
    INDEX
    Explanations

    references to the game "PUBG" and its associated content

    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
    олÑĮко
    -0.07
    outers
    -0.07
    porte
    -0.07
    fea
    -0.07
    mina
    -0.06
    aad
    -0.06
    agna
    -0.06
    IFn
    -0.06
    izo
    -0.06
    atures
    -0.06
    POSITIVE LOGITS
    lix
    0.08
    isher
    0.07
    lik
    0.07
    lius
    0.07
    erty
    0.07
    /Sub
    0.07
    lisi
    0.07
    lsi
    0.07
    untu
    0.07
    lili
    0.07
    Activations Density 0.004%

    No Known Activations