© 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. 9-LLAMASCOPE-RES-131K
    11. 97202
    Prev
    Next
    INDEX
    Explanations

    references to specific entities or titles, particularly in entertainment or technology contexts

    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
    avax
    -0.08
    egal
    -0.07
    ardown
    -0.07
    itary
    -0.07
    vette
    -0.07
    tplib
    -0.07
     Fay
    -0.07
    aoke
    -0.06
    eses
    -0.06
    egra
    -0.06
    POSITIVE LOGITS
    apt
    0.06
    å¹³æĪIJ
    0.06
     molec
    0.06
     multiline
    0.06
    275
    0.06
     Olsen
    0.06
     montage
    0.06
     nackt
    0.06
    LOPT
    0.06
    rosso
    0.06
    Activations Density 0.001%

    No Known Activations