© 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. 124509
    Prev
    Next
    INDEX
    Explanations

    specific numerical addresses and identifiers

    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
    éré
    -0.07
    mates
    -0.07
    velle
    -0.06
    osphate
    -0.06
    irie
    -0.06
    onor
    -0.06
    icate
    -0.06
    angles
    -0.06
    kü
    -0.06
    uhan
    -0.06
    POSITIVE LOGITS
    leta
    0.08
    onta
    0.08
    ial
    0.07
    Occurred
    0.07
    opsy
    0.07
    LET
    0.07
    ÙĦ
    0.06
    atic
    0.06
    лÑıеÑĤ
    0.06
    WG
    0.06
    Activations Density 0.026%

    No Known Activations