© 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. 60809
    Prev
    Next
    INDEX
    Explanations

    terms related to medical treatments and therapies

    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
    umu
    -0.08
    oes
    -0.07
    ิà¸ļ
    -0.07
    appen
    -0.07
    assin
    -0.07
    sei
    -0.07
     VÅ¡
    -0.06
    okt
    -0.06
    109
    -0.06
    redo
    -0.06
    POSITIVE LOGITS
    icamente
    0.07
    estination
    0.06
    CodeAt
    0.06
    lando
    0.06
     treating
    0.06
    outil
    0.06
    options
    0.06
     HS
    0.06
    485
    0.06
    -options
    0.06
    Activations Density 0.014%

    No Known Activations