© 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. 27550
    Prev
    Next
    INDEX
    Explanations

    terms related to affiliate marketing and referral programs

    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
    erland
    -0.07
    urnal
    -0.07
    rale
    -0.07
    sheets
    -0.06
    576
    -0.06
    /issues
    -0.06
     Rac
    -0.06
    alf
    -0.06
    zi
    -0.06
    iga
    -0.06
    POSITIVE LOGITS
    SHIP
    0.08
     links
    0.07
    irut
    0.07
    itos
    0.07
    lád
    0.07
    isay
    0.07
     link
    0.07
    bler
    0.07
    iasi
    0.07
    جÙħØ©
    0.07
    Activations Density 0.001%

    No Known Activations