© 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. 92940
    Prev
    Next
    INDEX
    Explanations

    references to specific places and people associated with personal memories or experiences

    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
    ellen
    -0.06
     popular
    -0.06
    thes
    -0.06
     motion
    -0.06
     highly
    -0.05
     currently
    -0.05
    Compiled
    -0.05
     void
    -0.05
     :-↵
    -0.05
     ex
    -0.05
    POSITIVE LOGITS
     sede
    0.09
    íĥĿ
    0.09
    __$
    0.08
    lant
    0.08
    rys
    0.08
    .byId
    0.08
    ÑĤого
    0.08
     گرÙģ
    0.08
    å¾Ħ
    0.08
    adan
    0.08
    Activations Density 0.002%

    No Known Activations