© 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. 71954
    Prev
    Next
    INDEX
    Explanations

    references to technology and product specifications

    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
    essel
    -0.07
    fty
    -0.06
     prote
    -0.06
    perm
    -0.06
     revolt
    -0.06
    Proto
    -0.06
    porte
    -0.06
    asc
    -0.06
    particle
    -0.06
    ovy
    -0.06
    POSITIVE LOGITS
     grown
    0.08
     wa
    0.08
     Sapphire
    0.08
     addCriterion
    0.07
    grown
    0.07
     Kaynak
    0.07
     Cree
    0.07
     Qualität
    0.07
    .gt
    0.07
    åħ
    0.07
    Activations Density 0.027%

    No Known Activations