© 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. 22-LLAMASCOPE-RES-131K
    11. 3747
    Prev
    Next
    INDEX
    Explanations

    references to "junk" or "junkie" in various contexts

    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
    ically
    -0.07
    izations
    -0.07
    atically
    -0.07
    zens
    -0.07
    raig
    -0.06
    IZE
    -0.06
    clip
    -0.06
     風
    -0.06
    __/
    -0.06
    HING
    -0.06
    POSITIVE LOGITS
    yard
    0.13
    yards
    0.10
    ie
    0.09
    adel
    0.09
    ies
    0.08
    ed
    0.08
     yard
    0.08
    iez
    0.08
    uet
    0.07
    edin
    0.07
    Activations Density 0.003%

    No Known Activations