© 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. 98702
    Prev
    Next
    INDEX
    Explanations

    indications of absence or lack of interactions

    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
     cort
    -0.06
    illaume
    -0.06
    en
    -0.06
    it
    -0.05
    759
    -0.05
    kus
    -0.05
    640
    -0.05
    pl
    -0.05
     Cort
    -0.05
    ui
    -0.05
    POSITIVE LOGITS
    VRT
    0.08
    IID
    0.08
     infinit
    0.07
    emean
    0.07
    aleur
    0.07
    .until
    0.07
     Pru
    0.07
    amilia
    0.07
    _kv
    0.07
    .ta
    0.07
    Activations Density 0.010%

    No Known Activations