© 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. 98857
    Prev
    Next
    INDEX
    Explanations

    references to social media and online community dynamics

    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
    _DEFINED
    -0.08
    ahat
    -0.08
    å³°
    -0.08
    iag
    -0.07
    eca
    -0.07
    azo
    -0.07
    leme
    -0.07
    tü
    -0.07
    Ñıви
    -0.07
    zet
    -0.07
    POSITIVE LOGITS
     without
    0.06
    idon
    0.06
     at
    0.06
     Ou
    0.05
     tobacco
    0.05
     pushed
    0.05
     Maint
    0.05
     n
    0.05
     Market
    0.05
    766
    0.05
    Activations Density 0.001%

    No Known Activations