© 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. 83644
    Prev
    Next
    INDEX
    Explanations

    phrases related to the ideal or best choices in products or services

    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
    gard
    -0.08
    stoup
    -0.08
    edback
    -0.07
    osed
    -0.07
    ogui
    -0.07
     Sez
    -0.07
    ensed
    -0.06
     недел
    -0.06
    -placeholder
    -0.06
    odos
    -0.06
    POSITIVE LOGITS
     solution
    0.09
    -fit
    0.08
    -su
    0.07
    .solution
    0.07
    ÂĿ
    0.07
     compromises
    0.07
     match
    0.07
    aber
    0.07
    (s
    0.06
    solution
    0.06
    Activations Density 0.010%

    No Known Activations