© 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 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. 106672
    Prev
    Next
    INDEX
    Explanations

    phrases related to comparisons and system configurations

    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
    alth
    -0.07
    umph
    -0.07
     lately
    -0.07
     Ø®ÙĪاÙĩÙĨد
    -0.06
    esub
    -0.06
     Richardson
    -0.06
     budou
    -0.06
    beit
    -0.06
     doubles
    -0.06
     Serialized
    -0.06
    POSITIVE LOGITS
    EATURE
    0.07
    å¥
    0.06
    Filename
    0.06
    Humans
    0.06
    chor
    0.06
    osi
    0.06
    imeline
    0.06
    оваÑĢ
    0.06
    enna
    0.06
     humans
    0.06
    Activations Density 0.013%

    No Known Activations