© 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 EvalsExportsAPI 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. 29018
    Prev
    Next
    INDEX
    Explanations

    interactions and emotional connections between characters

    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
     my
    -0.08
     Ive
    -0.07
     Ñĥм
    -0.07
    emean
    -0.06
    afb
    -0.06
    æĪijçļĦ
    -0.06
    imes
    -0.06
    rypted
    -0.06
    inalg
    -0.06
    aho
    -0.06
    POSITIVE LOGITS
    upert
    0.07
     himself
    0.06
     jim
    0.06
     Demir
    0.06
    æºĸ
    0.06
     felt
    0.06
    è§īå¾Ĺ
    0.06
     بÙĪابة
    0.06
    errick
    0.06
    ÏĦÎŃλε
    0.06
    Activations Density 0.079%

    No Known Activations