© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 961
    Prev
    Next
    INDEX
    Explanations

    phrases related to affiliate marketing and commissions

    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
    oles
    -0.06
     for
    -0.06
    rico
    -0.06
     Clement
    -0.06
    leaf
    -0.06
    ấm
    -0.06
     master
    -0.05
    /extensions
    -0.05
     Carroll
    -0.05
    ave
    -0.05
    POSITIVE LOGITS
    ãĥijãĥ³
    0.08
    ê¶ģ
    0.07
    .idea
    0.07
    woff
    0.07
     Kush
    0.07
    adius
    0.07
    lab
    0.06
    ëī´ìĬ¤
    0.06
    ãĤ·ãĥ§ãĥ³
    0.06
    -www
    0.06
    Activations Density 0.005%

    No Known Activations