© 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. 608
    Prev
    Next
    INDEX
    Explanations

    nouns and phrases related to contributions and collaborations

    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
    leck
    -0.07
    ILLE
    -0.07
     bog
    -0.06
    ickness
    -0.06
    çħ
    -0.06
    nem
    -0.06
    bye
    -0.06
     Bias
    -0.06
     дог
    -0.06
     fidelity
    -0.06
    POSITIVE LOGITS
     overall
    0.09
    overall
    0.08
    agal
    0.07
    alist
    0.07
    849
    0.06
     effort
    0.06
     efforts
    0.06
    alon
    0.06
    adro
    0.06
     literature
    0.06
    Activations Density 0.020%

    No Known Activations