© 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. 98690
    Prev
    Next
    INDEX
    Explanations

    numerical values and legal statutes

    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
    OAD
    -0.08
    imb
    -0.07
    iga
    -0.07
    iya
    -0.06
    ahlen
    -0.06
    kus
    -0.06
    inia
    -0.06
     Prote
    -0.06
     rowspan
    -0.06
     NotSupportedException
    -0.06
    POSITIVE LOGITS
    otts
    0.08
    ãģĭãģĹ
    0.07
    .xr
    0.06
     sebou
    0.06
    illes
    0.06
    ellido
    0.06
    roit
    0.06
    -State
    0.06
    zz
    0.06
     èŃ
    0.06
    Activations Density 0.012%

    No Known Activations