© 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. 127194
    Prev
    Next
    INDEX
    Explanations

    repeated numerical data or statistics

    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
    imers
    -0.08
    annis
    -0.07
    oor
    -0.07
    imer
    -0.07
    uner
    -0.07
    seau
    -0.07
     Demand
    -0.06
     Gabriel
    -0.06
    adir
    -0.06
    .opendaylight
    -0.06
    POSITIVE LOGITS
    å¹´
    0.07
    aling
    0.07
    uÃŃ
    0.07
     dated
    0.06
     Slee
    0.06
    Bindable
    0.06
    race
    0.06
    ög
    0.06
    sher
    0.06
    ëħĦ
    0.06
    Activations Density 0.037%

    No Known Activations