© 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. 129207
    Prev
    Next
    INDEX
    Explanations

    variations of the word "otherwise" in various contexts

    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
    ervo
    -0.07
    sg
    -0.07
    inch
    -0.06
    ãĥ¼ãĥijãĥ¼
    -0.06
    elow
    -0.06
    lessly
    -0.06
    reta
    -0.06
     McCarthy
    -0.06
    arse
    -0.06
    еÑĢп
    -0.06
    POSITIVE LOGITS
    isinde
    0.07
    raž
    0.07
    misc
    0.07
    ÙĬÙĨ
    0.07
    pagesize
    0.07
    otre
    0.07
     crem
    0.06
    à¸Ńà¸ĩ
    0.06
     ÄIJặc
    0.06
    áºŃt
    0.06
    Activations Density 0.002%

    No Known Activations