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. 5603
    Prev
    Next
    INDEX
    Explanations

    references to patio-related items and concepts

    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
    me
    -0.09
    fully
    -0.07
    tracks
    -0.07
    mie
    -0.07
    ment
    -0.07
    roe
    -0.07
    ri
    -0.07
    ments
    -0.07
    ple
    -0.06
    pled
    -0.06
    POSITIVE LOGITS
     furniture
    0.08
    ulumi
    0.08
    /back
    0.07
    embros
    0.07
     umbrella
    0.07
    imson
    0.07
    avra
    0.07
    ehler
    0.07
    dek
    0.06
    urniture
    0.06
    Activations Density 0.002%

    No Known Activations