© 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. 17-LLAMASCOPE-RES-131K
    11. 61256
    Prev
    Next
    INDEX
    Explanations

    comparisons of performance or outcomes across different contexts or instances

    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
    ela
    -0.07
    ames
    -0.07
     vš
    -0.06
     Mans
    -0.05
    enge
    -0.05
    ahl
    -0.05
     Garn
    -0.05
    dera
    -0.05
     Remaining
    -0.05
     Dec
    -0.05
    POSITIVE LOGITS
     previous
    0.19
     Previous
    0.17
    Previous
    0.17
    previous
    0.17
    .previous
    0.15
    (previous
    0.14
     predecessor
    0.14
     last
    0.13
     попеÑĢед
    0.13
    _previous
    0.12
    Activations Density 0.103%

    No Known Activations