© 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. 59115
    Prev
    Next
    INDEX
    Explanations

    sections or phrases related to authorship and attribution

    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
    enga
    -0.07
    ecut
    -0.06
    fty
    -0.06
     cáºŃn
    -0.06
    imo
    -0.06
    isco
    -0.06
    onda
    -0.06
    iac
    -0.06
     Kann
    -0.06
    er
    -0.05
    POSITIVE LOGITS
     INLINE
    0.08
    _AUTHOR
    0.08
    ROTO
    0.07
    ptype
    0.07
    èĴ
    0.07
    ázev
    0.07
    /*č↵
    0.07
    ä½ľèĢħ
    0.07
     sev
    0.07
    LObject
    0.07
    Activations Density 0.002%

    No Known Activations