© 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 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. 29313
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Posted" indicating publication or announcement dates in various contexts

    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
    ides
    -0.08
    Sit
    -0.06
    ib
    -0.06
     ef
    -0.06
    ump
    -0.06
    ear
    -0.06
     Sit
    -0.06
    944
    -0.06
    453
    -0.06
    es
    -0.06
    POSITIVE LOGITS
    .scalablytyped
    0.08
    ystick
    0.08
    chyb
    0.07
    alth
    0.07
     reife
    0.07
     nackte
    0.07
    곤
    0.07
    Frameworks
    0.07
    κι
    0.07
    .her
    0.07
    Activations Density 0.006%

    No Known Activations