© 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. 92810
    Prev
    Next
    INDEX
    Explanations

    sentences that contain significant consequences or outcomes

    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
     similarly
    -0.06
     or
    -0.06
     consisting
    -0.05
     Similarly
    -0.05
     или
    -0.05
    arden
    -0.05
    302
    -0.05
     Firstly
    -0.05
     workaround
    -0.05
     Related
    -0.05
    POSITIVE LOGITS
     etc
    0.14
    etc
    0.12
    Plus
    0.11
     Plus
    0.11
     PLUS
    0.10
    plus
    0.10
     plus
    0.10
    PLUS
    0.09
    ëĵ±
    0.08
    _plus
    0.08
    Activations Density 0.140%

    No Known Activations