© 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. 69783
    Prev
    Next
    INDEX
    Explanations

    references to posts or articles

    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
    oct
    -0.07
    enet
    -0.07
    quil
    -0.07
    amin
    -0.07
     Declare
    -0.07
    ãĤħ
    -0.06
    encias
    -0.06
    ober
    -0.06
    ÅĻeh
    -0.06
    Dados
    -0.06
    POSITIVE LOGITS
    aeper
    0.06
    baum
    0.06
     gloss
    0.06
    èIJ½
    0.06
    liness
    0.06
     Lair
    0.05
    adesh
    0.05
    kas
    0.05
    :frame
    0.05
    ould
    0.05
    Activations Density 0.000%

    No Known Activations