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. 44292
    Prev
    Next
    INDEX
    Explanations

    expressions related to evidence or demonstration in scientific contexts

    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
    antics
    -0.07
    Úĺ
    -0.07
    /of
    -0.07
    å°½
    -0.07
    bef
    -0.07
     DESCRIPTION
    -0.07
     ofApp
    -0.07
    екÑĤÑĥ
    -0.07
    ấp
    -0.07
    ohon
    -0.06
    POSITIVE LOGITS
     that
    0.14
     how
    0.13
    that
    0.11
     why
    0.11
     using
    0.10
     analy
    0.10
    how
    0.10
     convinc
    0.09
     theoretically
    0.09
     empir
    0.09
    Activations Density 0.071%

    No Known Activations