© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 15-LLAMASCOPE-RES-131K
    11. 104386
    Prev
    Next
    INDEX
    Explanations

    indicators of errors in code or system processes

    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
    à¥įà¤Łà¤°
    -0.07
    @update
    -0.07
    arger
    -0.07
    èī¦
    -0.07
    htub
    -0.06
    iculo
    -0.06
    омеÑĤ
    -0.06
    ENU
    -0.06
    enga
    -0.06
    aÄĩ
    -0.06
    POSITIVE LOGITS
    MBProgressHUD
    0.06
    137
    0.06
     Braun
    0.06
    spo
    0.06
     Marl
    0.06
    ovan
    0.06
     Boyle
    0.06
    Bootstrap
    0.06
    503
    0.06
    nk
    0.06
    Activations Density 0.000%

    No Known Activations