© 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. 55942
    Prev
    Next
    INDEX
    Explanations

    topics related to personal challenges and responsibilities

    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
     sometimes
    -0.07
    sometimes
    -0.06
    Ãļ
    -0.06
    vd
    -0.06
    Sometimes
    -0.06
     Sometimes
    -0.06
    opus
    -0.06
    abei
    -0.06
    Always
    -0.06
    okoj
    -0.06
    POSITIVE LOGITS
     tomorrow
    0.10
     tonight
    0.10
     upcoming
    0.09
    üss
    0.08
     forthcoming
    0.07
    elin
    0.07
     soon
    0.07
     unintended
    0.07
    enler
    0.07
    ä¸ĭåİ»
    0.07
    Activations Density 0.033%

    No Known Activations