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. 44372
    Prev
    Next
    INDEX
    Explanations

    phrases indicating uncertainty or hesitation

    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
     greatly
    -0.07
    ãĤĪãĤĬ
    -0.07
    æĽ´
    -0.07
    more
    -0.07
     slightly
    -0.07
     almost
    -0.07
     immensely
    -0.07
     particularly
    -0.07
     increasingly
    -0.07
    æĽ´åĬł
    -0.07
    POSITIVE LOGITS
     yet
    0.09
     sure
    0.09
     so
    0.08
    yet
    0.08
     ready
    0.08
     what
    0.08
     enough
    0.07
     as
    0.07
     like
    0.07
     finished
    0.07
    Activations Density 0.010%

    No Known Activations