© 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. 61310
    Prev
    Next
    INDEX
    Explanations

    references to links or connections in a discussion about geometry or programming

    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
    å¿Ĺ
    -0.07
    simd
    -0.07
    resse
    -0.07
     ì¡
    -0.07
     æ
    -0.07
    utschen
    -0.07
     Datum
    -0.07
    lisi
    -0.07
     Circular
    -0.07
    .gstatic
    -0.06
    POSITIVE LOGITS
    ition
    0.07
    enta
    0.06
     pec
    0.06
     Virt
    0.06
    lon
    0.06
    virt
    0.05
     Spring
    0.05
    edin
    0.05
    atl
    0.05
     Wan
    0.05
    Activations Density 0.000%

    No Known Activations