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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 97321
    Prev
    Next
    INDEX
    Explanations

    phrases related to marketing or readership engagement

    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
    yx
    -0.06
     ben
    -0.06
     mainland
    -0.06
    ãĥ¼ãĥ
    -0.06
    mand
    -0.06
    ACP
    -0.05
     Sud
    -0.05
    idades
    -0.05
     judgement
    -0.05
     chatt
    -0.05
    POSITIVE LOGITS
    antha
    0.09
    ushi
    0.07
    nika
    0.07
    .fin
    0.07
    REMOVE
    0.07
    /Dk
    0.07
     ÚĺاÙĨ
    0.07
    alfa
    0.07
    ksam
    0.07
     Kosten
    0.06
    Activations Density 0.003%

    No Known Activations