© 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. 84481
    Prev
    Next
    INDEX
    Explanations

    phrases related to creative input and customization options

    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
    prm
    -0.07
    bruar
    -0.06
     Ful
    -0.06
    »
    -0.06
    ableView
    -0.06
    jev
    -0.06
    ov
    -0.06
    LD
    -0.06
    "bytes
    -0.06
    isos
    -0.06
    POSITIVE LOGITS
    ismo
    0.07
    .embed
    0.07
     Elli
    0.07
    vanced
    0.06
     pens
    0.06
    ãn
    0.06
     weather
    0.06
    -prepend
    0.06
    ãĥ¼ãĥĬ
    0.06
     McCl
    0.06
    Activations Density 0.006%

    No Known Activations