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. 43396
    Prev
    Next
    INDEX
    Explanations

    phrases and words related to anticipation or waiting for something

    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
    errer
    -0.07
    erken
    -0.07
    alace
    -0.06
    illion
    -0.06
    uÅŁ
    -0.06
    -Clause
    -0.06
    mamak
    -0.06
    ernel
    -0.06
     lesb
    -0.06
    usu
    -0.06
    POSITIVE LOGITS
     years
    0.12
     anx
    0.11
     months
    0.11
     impatient
    0.10
     eagerly
    0.10
     decades
    0.10
     patiently
    0.10
    æľŁå¾ħ
    0.10
     lifetime
    0.09
     YEARS
    0.09
    Activations Density 0.013%

    No Known Activations