© 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. 15-LLAMASCOPE-RES-131K
    11. 62207
    Prev
    Next
    INDEX
    Explanations

    special characters and formatting elements in the text

    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
    ylon
    -0.07
    ookie
    -0.07
    isci
    -0.07
    acas
    -0.07
    afka
    -0.07
    ilot
    -0.07
    HONE
    -0.07
    ensor
    -0.06
    ideo
    -0.06
    éli
    -0.06
    POSITIVE LOGITS
    inke
    0.06
     Klo
    0.05
    ollah
    0.05
     Rut
    0.05
     Bun
    0.05
     vt
    0.05
     ,
    0.05
     Mr
    0.05
     expiry
    0.05
    NSE
    0.05
    Activations Density 0.034%

    No Known Activations