© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 92705
    Prev
    Next
    INDEX
    Explanations

    phrases related to restrictions and limitations on offers or returns

    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
    mtree
    -0.09
    ainen
    -0.08
    алÑĭ
    -0.07
    erus
    -0.07
     kvin
    -0.07
    artz
    -0.07
    acios
    -0.07
    ARNING
    -0.07
    LETE
    -0.07
    ombok
    -0.07
    POSITIVE LOGITS
     combined
    0.07
    comb
    0.07
     combination
    0.07
     Comb
    0.06
     Combined
    0.06
     nor
    0.06
    éĢı
    0.06
     combines
    0.06
    combined
    0.06
    UPI
    0.06
    Activations Density 0.004%

    No Known Activations