© 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. 41055
    Prev
    Next
    INDEX
    Explanations

    terms related to crowdfunding and collaboration

    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
    utow
    -0.07
    zelf
    -0.07
    iele
    -0.07
    ãĥ©ãĥ³ãĥī
    -0.07
    ansi
    -0.07
     GetHashCode
    -0.07
    пеÑĩ
    -0.07
     ArgumentNullException
    -0.07
    (balance
    -0.07
    aser
    -0.07
    POSITIVE LOGITS
    ourced
    0.07
    Ñīин
    0.06
    dera
    0.06
     eng
    0.06
    fare
    0.06
    hound
    0.06
    ourcing
    0.06
     deficit
    0.06
     platform
    0.06
    ishly
    0.06
    Activations Density 0.004%

    No Known Activations