© 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 EvalsExportsinterp-engineNEWAPI 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. 5089
    Prev
    Next
    INDEX
    Explanations

    phrases related to solutions and their effectiveness

    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
    ampo
    -0.06
    ewire
    -0.06
    atform
    -0.06
    женÑĮ
    -0.06
    еÑģÑĤи
    -0.06
    tring
    -0.06
    ResourceManager
    -0.06
    üml
    -0.06
    offsetof
    -0.06
    _EXPORT
    -0.06
    POSITIVE LOGITS
     effectiveness
    0.15
     effective
    0.15
    -effective
    0.12
     Effective
    0.11
     efficacy
    0.11
    æľīæķĪ
    0.10
    effective
    0.10
     effic
    0.10
     works
    0.10
     efect
    0.10
    Activations Density 0.051%

    No Known Activations