© 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. 9-LLAMASCOPE-RES-131K
    11. 95804
    Prev
    Next
    INDEX
    Explanations

    mathematical and programming expressions related to conditional statements and evaluations

    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
    zl
    -0.08
    acades
    -0.06
    lix
    -0.06
    emas
    -0.06
    _kw
    -0.06
    xis
    -0.06
    haar
    -0.06
    евиÑĩ
    -0.06
    Credit
    -0.06
    pekt
    -0.06
    POSITIVE LOGITS
    iers
    0.07
     اÙĦÙĩ
    0.07
    ipv
    0.07
    utt
    0.06
    -lang
    0.06
    .Factory
    0.06
    ugged
    0.06
    /downloads
    0.06
     Shine
    0.06
    _vm
    0.06
    Activations Density 0.054%

    No Known Activations