© 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. 17-LLAMASCOPE-RES-131K
    11. 29001
    Prev
    Next
    INDEX
    Explanations

    references to organized groups and their activities

    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
    mdb
    -0.06
    RR
    -0.06
     Spo
    -0.06
     newest
    -0.06
    ELY
    -0.06
    vit
    -0.06
    anken
    -0.06
    elan
    -0.06
     Prediction
    -0.06
    âm
    -0.06
    POSITIVE LOGITS
    Ñĩин
    0.08
    ãĥ¶
    0.08
    reff
    0.08
    /tos
    0.07
    _CNTL
    0.07
    ÙĬÙĤ
    0.07
     realm
    0.06
    .obtain
    0.06
    rador
    0.06
    ADF
    0.06
    Activations Density 0.000%

    No Known Activations