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. 43685
    Prev
    Next
    INDEX
    Explanations

    words related to hospitality and food service, particularly cocktails and drinks

    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
    TRGL
    -0.10
    ewise
    -0.08
    alette
    -0.08
    ERRQ
    -0.08
    KANJI
    -0.08
    ing
    -0.08
    /animations
    -0.07
    utut
    -0.07
    EMPLARY
    -0.07
    etten
    -0.07
    POSITIVE LOGITS
     AT
    0.10
     ARISING
    0.10
    ’S
    0.10
     OF
    0.10
     HOLDERS
    0.09
     CAUSED
    0.09
     THROUGH
    0.09
     VIA
    0.09
    'S
    0.09
    OF
    0.09
    Activations Density 0.077%

    No Known Activations