© 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. 95208
    Prev
    Next
    INDEX
    Explanations

    contractions of "is" and "has."

    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
    idor
    -0.08
    trace
    -0.07
    robat
    -0.07
    sume
    -0.07
    181
    -0.07
    ãĤµãĤ¤
    -0.07
    udur
    -0.07
    éĻµ
    -0.07
    igel
    -0.07
    æ±Ĺ
    -0.07
    POSITIVE LOGITS
     por
    0.06
     else
    0.06
     who
    0.06
     heter
    0.06
    ef
    0.06
    osh
    0.06
     whom
    0.05
    por
    0.05
     fault
    0.05
    ension
    0.05
    Activations Density 0.006%

    No Known Activations