Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 82874
    Prev
    Next
    INDEX
    Explanations

    activities related to social gatherings and entertainment

    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
    ÐĴÐŀ
    -0.06
    itur
    -0.06
    ryn
    -0.06
    it
    -0.06
    ampler
    -0.05
    alus
    -0.05
     Crescent
    -0.05
     constant
    -0.05
    iola
    -0.05
    IDS
    -0.05
    POSITIVE LOGITS
    Friends
    0.08
     friends
    0.08
    riends
    0.08
     Friends
    0.07
    aggio
    0.07
    æŀ¶
    0.07
    739
    0.07
    ephir
    0.07
     parties
    0.07
     Hlav
    0.07
    Activations Density 0.002%

    No Known Activations