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. 44382
    Prev
    Next
    INDEX
    Explanations

    terms related to assistance and support

    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
    TERS
    -0.06
    _refl
    -0.06
    inspace
    -0.06
    _OF
    -0.06
    uild
    -0.06
    -of
    -0.06
    -than
    -0.05
    _OPTS
    -0.05
    ucha
    -0.05
    jh
    -0.05
    POSITIVE LOGITS
     provided
    0.09
     afforded
    0.09
     and
    0.08
     primarily
    0.08
     offered
    0.07
    FromArray
    0.07
     گرÙģØªÙĨ
    0.07
     ofrec
    0.07
     mainly
    0.07
     supplied
    0.07
    Activations Density 0.017%

    No Known Activations