© 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. 9-LLAMASCOPE-RES-131K
    11. 94599
    Prev
    Next
    INDEX
    Explanations

    concepts related to existence and the validity of certain terms or ideas

    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
    immel
    -0.07
    ables
    -0.07
     Rin
    -0.06
    FN
    -0.06
     salute
    -0.06
    peats
    -0.06
    STEM
    -0.06
     Hobby
    -0.06
    osaurs
    -0.06
    prises
    -0.05
    POSITIVE LOGITS
     Exist
    0.09
     existence
    0.09
     Exists
    0.08
    Exist
    0.08
    .exist
    0.08
     existe
    0.07
     exist
    0.07
     exists
    0.07
    Exists
    0.07
    åŃĺåľ¨
    0.07
    Activations Density 0.047%

    No Known Activations