© 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. 98156
    Prev
    Next
    INDEX
    Explanations

    sentences expressing reassurance or solutions to concerns

    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
    ecc
    -0.06
    [source
    -0.06
    andle
    -0.06
    ep
    -0.06
     perÃŃ
    -0.06
     lit
    -0.06
    æłı
    -0.06
    .struts
    -0.06
     pitched
    -0.06
    akra
    -0.06
    POSITIVE LOGITS
    ecz
    0.07
    forme
    0.07
    973
    0.07
    atak
    0.07
    ewire
    0.07
    ä»ĭ
    0.06
    erville
    0.06
    577
    0.06
    asure
    0.06
    edio
    0.06
    Activations Density 0.006%

    No Known Activations