© 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. 82855
    Prev
    Next
    INDEX
    Explanations

    phrases related to consultations and project discussions

    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
    yang
    -0.08
    èm
    -0.07
    åde
    -0.07
    íĽĦ기
    -0.07
    онÑĮ
    -0.07
    _regeneration
    -0.07
    åŁŁ
    -0.06
    -dist
    -0.06
     maduras
    -0.06
    _DIST
    -0.06
    POSITIVE LOGITS
     your
    0.07
     options
    0.07
     any
    0.07
     sor
    0.07
     Sor
    0.06
     whether
    0.06
     situation
    0.06
     further
    0.06
    Dirty
    0.06
    843
    0.06
    Activations Density 0.005%

    No Known Activations