© 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. 124034
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing community and collective experiences

    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
    yw
    -0.08
    æħ
    -0.07
    deo
    -0.07
    batim
    -0.07
    edback
    -0.07
    ãĥ¼ãĥķ
    -0.07
     Ulus
    -0.07
    leon
    -0.06
    orz
    -0.06
    xcb
    -0.06
    POSITIVE LOGITS
     therefore
    0.07
    osal
    0.07
    åIJ§
    0.06
    åºĦ
    0.06
     donc
    0.06
     concent
    0.06
     be
    0.06
     abund
    0.06
    IDL
    0.06
     note
    0.05
    Activations Density 0.020%

    No Known Activations