© 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. 95662
    Prev
    Next
    INDEX
    Explanations

    high activation multiple comments and code segments

    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
    l
    -0.08
    s
    -0.08
    ic
    -0.08
    Ø©
    -0.07
    z
    -0.07
    d
    -0.07
    ãģĵãĤį
    -0.07
    j
    -0.06
    itre
    -0.06
    ly
    -0.06
    POSITIVE LOGITS
    roperty
    0.07
    braco
    0.07
    _ASSUME
    0.07
     !***
    0.07
    AGEMENT
    0.07
    olik
    0.07
    ategorized
    0.07
    rome
    0.07
    stal
    0.07
    ncia
    0.06
    Activations Density 0.055%

    No Known Activations