© 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. 92802
    Prev
    Next
    INDEX
    Explanations

    references to media credibility or accountability

    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
    503
    -0.07
    465
    -0.06
    504
    -0.06
    ög
    -0.06
    gli
    -0.06
    esse
    -0.05
    ena
    -0.05
    UnderTest
    -0.05
    ENCHMARK
    -0.05
    .Transparent
    -0.05
    POSITIVE LOGITS
    tae
    0.08
    ":[{↵
    0.07
    MOTE
    0.07
    å¼±
    0.07
     scoop
    0.07
    =email
    0.07
     sco
    0.07
     assignment
    0.07
     assignable
    0.07
    ateria
    0.07
    Activations Density 0.001%

    No Known Activations