© 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. 17-LLAMASCOPE-RES-131K
    11. 124758
    Prev
    Next
    INDEX
    Explanations

    terms related to social media and networking

    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
    ALER
    -0.07
    Shock
    -0.07
    aler
    -0.06
    ilton
    -0.06
    /jav
    -0.06
    Ñľ
    -0.06
    imon
    -0.06
    stown
    -0.06
     Shock
    -0.06
    irling
    -0.06
    POSITIVE LOGITS
    adele
    0.07
    eden
    0.06
    sci
    0.06
     Cem
    0.06
    reds
    0.06
    jer
    0.06
    иÑģк
    0.06
    Ñħ
    0.06
    fer
    0.05
    referer
    0.05
    Activations Density 0.005%

    No Known Activations