© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 77549
    Prev
    Next
    INDEX
    Explanations

    phrases related to communication and information exchange

    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
    acher
    -0.06
     lur
    -0.06
    undi
    -0.06
    erc
    -0.06
    ương
    -0.05
    bilt
    -0.05
     prank
    -0.05
     Fancy
    -0.05
    extras
    -0.05
     Miller
    -0.05
    POSITIVE LOGITS
     frequently
    0.13
     frequent
    0.10
     freq
    0.10
     encountered
    0.09
     often
    0.09
     encounter
    0.09
     Frequently
    0.09
    é¢ij
    0.09
    éł»
    0.09
     encounters
    0.09
    Activations Density 0.045%

    No Known Activations