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. 11492
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing the quality or benefits of a product or service

    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
     unbearable
    -0.07
    ndx
    -0.06
    TOTYPE
    -0.06
    rightness
    -0.06
    eÅŁit
    -0.06
    zá
    -0.06
    onet
    -0.06
     happiest
    -0.06
    illis
    -0.06
    eking
    -0.06
    POSITIVE LOGITS
     great
    0.14
     sure
    0.12
     excellent
    0.10
     win
    0.10
     cost
    0.10
     way
    0.10
     smart
    0.10
     must
    0.10
     quick
    0.10
     breeze
    0.10
    Activations Density 0.033%

    No Known Activations