© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 1150
    Prev
    Next
    INDEX
    Explanations

    references to information and details related to licenses and copyright

    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
    vert
    -0.06
    189
    -0.06
    009
    -0.06
    109
    -0.06
    215
    -0.05
    idia
    -0.05
     ðŁĻĤ
    -0.05
     AsyncCallback
    -0.05
    603
    -0.05
    å·
    -0.05
    POSITIVE LOGITS
    ascar
    0.08
    æĿŁ
    0.07
    _DEV
    0.07
    tight
    0.07
    DRV
    0.07
     åıĮ线
    0.07
    PCP
    0.07
    ικα
    0.07
    propTypes
    0.07
    kas
    0.07
    Activations Density 0.001%

    No Known Activations