© 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. 107955
    Prev
    Next
    INDEX
    Explanations

    phrases indicating personal experience or opinion

    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
    _SENS
    -0.06
    peÄį
    -0.06
     schön
    -0.06
    _initializer
    -0.06
    daÅŁ
    -0.06
    ä¸ī级
    -0.06
    åľŃ
    -0.06
     Quy
    -0.06
    mtree
    -0.06
    PRS
    -0.06
    POSITIVE LOGITS
     easy
    0.10
     easily
    0.09
     ease
    0.09
     easiest
    0.09
    easy
    0.08
     Easy
    0.08
     fácil
    0.07
    èĥ½åĬĽ
    0.07
    amiliar
    0.07
     snadno
    0.07
    Activations Density 0.056%

    No Known Activations