© 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. 42295
    Prev
    Next
    INDEX
    Explanations

    references to social interactions and experiences related to travel and exploration

    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
    ected
    -0.06
     fucking
    -0.06
    xes
    -0.06
     voks
    -0.06
    ?key
    -0.05
    idae
    -0.05
     Maj
    -0.05
    madan
    -0.05
    uran
    -0.05
    -indent
    -0.05
    POSITIVE LOGITS
    ç¦ģ
    0.08
     lately
    0.07
    edik
    0.07
    ÑĢив
    0.07
     trom
    0.07
    bere
    0.07
     ;č↵
    0.06
    etler
    0.06
    urre
    0.06
    Ùİد
    0.06
    Activations Density 0.010%

    No Known Activations