© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 127251
    Prev
    Next
    INDEX
    Explanations

    references to base64 encoding

    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
    amel
    -0.07
    elo
    -0.07
    ocs
    -0.07
    éľ²
    -0.07
    ition
    -0.07
     célib
    -0.06
    esto
    -0.06
    ether
    -0.06
    esi
    -0.06
    ather
    -0.06
    POSITIVE LOGITS
    dbg
    0.08
    .gdx
    0.07
    ProcessEvent
    0.07
    .twig
    0.07
     Nail
    0.06
    lesia
    0.06
    ESÄ°
    0.06
    /Base
    0.06
    .Std
    0.06
    LayoutConstraint
    0.06
    Activations Density 0.001%

    No Known Activations