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. 5476
    Prev
    Next
    INDEX
    Explanations

    references to previous statements or claims

    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
    -turned
    -0.08
    /or
    -0.07
    oretical
    -0.07
    agy
    -0.07
    ritz
    -0.06
    -than
    -0.06
    ovna
    -0.06
    sembl
    -0.06
     FindObjectOfType
    -0.06
    stitute
    -0.06
    POSITIVE LOGITS
    zelf
    0.10
    illions
    0.09
     же
    0.09
    -même
    0.08
    veral
    0.08
    ebek
    0.08
    maal
    0.07
    ".$_
    0.07
    neath
    0.07
    -chan
    0.07
    Activations Density 0.226%

    No Known Activations