© 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. 73343
    Prev
    Next
    INDEX
    Explanations

    phrases indicating product offerings and features

    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
    oba
    -0.06
    uries
    -0.06
    ho
    -0.06
     circulation
    -0.05
     Fa
    -0.05
    HR
    -0.05
    HI
    -0.05
     participates
    -0.05
    Fa
    -0.05
     Congress
    -0.05
    POSITIVE LOGITS
    upp
    0.08
     à¹ģà¸ģ
    0.07
    arnation
    0.07
    upos
    0.07
    κη
    0.07
    sov
    0.07
    ÙĪع
    0.07
     negot
    0.07
    iali
    0.07
    वत
    0.06
    Activations Density 0.005%

    No Known Activations