© 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. 87504
    Prev
    Next
    INDEX
    Explanations

    references to failures or shortcomings in various 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
    arken
    -0.09
    Nej
    -0.08
    /cs
    -0.08
    intree
    -0.08
     HOLDER
    -0.07
    .onResume
    -0.07
     å¸Ĥ
    -0.07
    ازÙĦ
    -0.07
    legate
    -0.07
    atsu
    -0.07
    POSITIVE LOGITS
    579
    0.08
    zed
    0.08
     to
    0.07
     ABC
    0.06
     Ade
    0.06
    ade
    0.06
     scr
    0.06
     of
    0.06
     tact
    0.06
    sto
    0.05
    Activations Density 0.008%

    No Known Activations