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. 44042
    Prev
    Next
    INDEX
    Explanations

    expressions related to coming to terms or accepting a situation

    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
    pedia
    -0.07
    cased
    -0.06
    ongyang
    -0.06
    ellar
    -0.06
    lint
    -0.06
    swick
    -0.06
    edList
    -0.06
    duction
    -0.06
    inki
    -0.06
    ãĥ¼ãĥª
    -0.06
    POSITIVE LOGITS
     grips
    0.15
     terms
    0.12
     grip
    0.11
     peace
    0.10
    rips
    0.09
     turns
    0.09
     Gri
    0.08
     closure
    0.08
     gras
    0.08
     Peace
    0.08
    Activations Density 0.008%

    No Known Activations