© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 40438
    Prev
    Next
    INDEX
    Explanations

    terms related to constraints and functions in different contexts

    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
    untu
    -0.09
    (æĹ¥
    -0.08
    446
    -0.08
    егоÑĢ
    -0.08
    unce
    -0.07
    Ñıд
    -0.07
    alion
    -0.07
     glUniform
    -0.07
     nonatomic
    -0.07
    nze
    -0.07
    POSITIVE LOGITS
     both
    0.14
    both
    0.12
     plus
    0.11
     Both
    0.10
    Both
    0.10
     cả
    0.10
     både
    0.09
     BOTH
    0.09
     beide
    0.09
    _BOTH
    0.09
    Activations Density 0.040%

    No Known Activations