© 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. 119510
    Prev
    Next
    INDEX
    Explanations

    mentions and references to Twitter and its usage

    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
    sub
    -0.07
    ÑĢаг
    -0.07
    ag
    -0.07
    elah
    -0.07
    avou
    -0.06
    лика
    -0.06
    éĺ
    -0.06
    ek
    -0.06
    serrat
    -0.06
     Kok
    -0.06
    POSITIVE LOGITS
    ati
    0.09
    verse
    0.08
    atti
    0.08
    osphate
    0.07
    ois
    0.07
    kest
    0.07
    /facebook
    0.07
    é³¥
    0.07
    izer
    0.07
    arti
    0.07
    Activations Density 0.007%

    No Known Activations