© 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. 26356
    Prev
    Next
    INDEX
    Explanations

    specific patterns or sequences in alphanumeric strings

    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
    ")));
    -0.08
    META
    -0.07
    //{{
    -0.07
    оÑĢÑıд
    -0.07
    recursive
    -0.06
    aise
    -0.06
    ifes
    -0.06
     @[
    -0.06
    зем
    -0.06
    qid
    -0.06
    POSITIVE LOGITS
    avel
    0.06
    ober
    0.06
    ë£Į
    0.05
    liked
    0.05
     patch
    0.05
     Speedway
    0.05
     Elect
    0.05
     scored
    0.05
    uges
    0.05
     Leslie
    0.05
    Activations Density 0.015%

    No Known Activations