© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 75331
    Prev
    Next
    INDEX
    Explanations

    key phrases and assertions related to societal and organizational issues

    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
     же
    -0.08
    Ø®Ùħ
    -0.07
     duly
    -0.07
    ãĤ¹ãĤ¿ãĥ¼
    -0.06
    itest
    -0.06
     Williamson
    -0.06
    claimer
    -0.06
    даÑı
    -0.06
    究
    -0.06
    _DECLARE
    -0.06
    POSITIVE LOGITS
     should
    0.07
    hari
    0.07
     shouldn
    0.07
    odon
    0.07
     surprisingly
    0.06
    LOGGER
    0.06
     Should
    0.06
    utter
    0.06
    should
    0.06
     pimp
    0.06
    Activations Density 0.019%

    No Known Activations