© 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. 9-LLAMASCOPE-RES-131K
    6. 95666
    Prev
    Next
    INDEX
    Explanations

    monetary values or amounts expressed in rupees

    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
    side
    -0.07
    ep
    -0.07
    ebo
    -0.07
    gether
    -0.07
    lessly
    -0.06
    lh
    -0.06
     erm
    -0.06
    ãĥ³ãĥĩ
    -0.06
     farming
    -0.06
    ————————————————
    -0.06
    POSITIVE LOGITS
    anness
    0.07
    vik
    0.07
    ushi
    0.07
    atoria
    0.06
    shal
    0.06
    ãĥ
    0.06
    olon
    0.06
     Sor
    0.06
    ĴĮ
    0.06
    -American
    0.06
    Activations Density 0.003%

    No Known Activations