© 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. 93117
    Prev
    Next
    INDEX
    Explanations

    punctuation and special characters related to navigation or downloads

    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
    ikk
    -0.07
    eroon
    -0.07
    atinum
    -0.06
    reibung
    -0.06
    URY
    -0.06
    pike
    -0.06
     Fry
    -0.06
    _epsilon
    -0.06
    aret
    -0.06
    ws
    -0.06
    POSITIVE LOGITS
    анÑĤи
    0.07
    _DETECT
    0.06
    ãĤĪãģ³
    0.06
    onas
    0.06
     baise
    0.06
    Multiplicity
    0.06
    è¹
    0.06
     Spy
    0.06
     maduras
    0.06
    ivid
    0.06
    Activations Density 0.000%

    No Known Activations