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. 44268
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and formatting indicators

    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
    IBC
    -0.06
    emm
    -0.06
    oft
    -0.06
    dorf
    -0.06
    ancy
    -0.06
    linger
    -0.06
    aster
    -0.06
    elden
    -0.06
    sher
    -0.06
    SearchTree
    -0.06
    POSITIVE LOGITS
     Fac
    0.09
     Tol
    0.08
    è§ī
    0.07
    олÑİ
    0.07
     Anadolu
    0.07
     Jewel
    0.06
     Odd
    0.06
    _via
    0.06
    ISC
    0.06
    ãĥªãĥ³ãĤ¯
    0.06
    Activations Density 0.005%

    No Known Activations