© 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. 40708
    Prev
    Next
    INDEX
    Explanations

    references to spoilers

    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
    unes
    -0.07
    upon
    -0.07
    vara
    -0.07
    propri
    -0.07
    pring
    -0.07
    awah
    -0.06
    gie
    -0.06
    istry
    -0.06
    elp
    -0.06
    mel
    -0.06
    POSITIVE LOGITS
    ific
    0.08
    icious
    0.08
    ously
    0.07
    æĢ§çļĦ
    0.07
    adic
    0.07
    ĵn
    0.07
    itical
    0.07
    ERCHANT
    0.07
    pedia
    0.06
    itious
    0.06
    Activations Density 0.003%

    No Known Activations