© 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. 125650
    Prev
    Next
    INDEX
    Explanations

    terms related to shipping and returns policies

    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
    _TAC
    -0.08
    ÙĤب
    -0.07
    ÃŁen
    -0.07
    853
    -0.07
    ÅĻeb
    -0.07
    ematik
    -0.07
    illos
    -0.07
    à¤Ĩà¤Ī
    -0.07
    æ¿ĥ
    -0.07
    ompiler
    -0.07
    POSITIVE LOGITS
    UNET
    0.07
    eref
    0.06
    ups
    0.06
     interven
    0.06
     fel
    0.06
     Doming
    0.06
     Duy
    0.05
    §
    0.05
    ocz
    0.05
     carousel
    0.05
    Activations Density 0.020%

    No Known Activations