© 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. 119844
    Prev
    Next
    INDEX
    Explanations

    phrases indicating support or assistance

    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
    ombie
    -0.07
    amiliar
    -0.07
    .Signal
    -0.06
     ãĥį
    -0.06
    eatures
    -0.06
     masa
    -0.06
    eature
    -0.06
     ÑĤоÑĩно
    -0.06
    xef
    -0.06
    ivery
    -0.06
    POSITIVE LOGITS
    mons
    0.07
     chronic
    0.07
    364
    0.07
     Floors
    0.06
    \Collections
    0.06
    alg
    0.06
    Thunk
    0.06
    864
    0.06
     constant
    0.06
    uner
    0.06
    Activations Density 0.008%

    No Known Activations