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. 44177
    Prev
    Next
    INDEX
    Explanations

    phrases indicating potential outcomes or results of actions

    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
    ecta
    -0.06
    erule
    -0.06
    nor
    -0.06
    ims
    -0.06
    ICA
    -0.06
    yor
    -0.06
    veloper
    -0.05
    continental
    -0.05
    ALA
    -0.05
    alar
    -0.05
    POSITIVE LOGITS
     fruition
    0.17
     pass
    0.15
     fruit
    0.13
     completion
    0.12
     reality
    0.12
     fr
    0.11
    fr
    0.11
     fruits
    0.11
     light
    0.11
     realization
    0.11
    Activations Density 0.008%

    No Known Activations