© 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. 17-LLAMASCOPE-RES-131K
    11. 127339
    Prev
    Next
    INDEX
    Explanations

    terms indicating approximation or estimation

    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
    hey
    -0.07
    asil
    -0.07
    вин
    -0.07
    htub
    -0.07
    vá
    -0.07
     absol
    -0.06
    озможно
    -0.06
    nst
    -0.06
    orem
    -0.06
     NÄĽm
    -0.06
    POSITIVE LOGITS
    LY
    0.07
    ç¿°
    0.07
     dozen
    0.07
    .dequeue
    0.07
     half
    0.07
     inv
    0.07
     correct
    0.06
    oire
    0.06
    izz
    0.06
    UnitTest
    0.06
    Activations Density 0.025%

    No Known Activations