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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 93479
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to access and availability

    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
    264
    -0.07
    çĭ¼
    -0.06
    andra
    -0.06
    ippy
    -0.06
     deja
    -0.06
    WithName
    -0.06
    tractor
    -0.05
     sec
    -0.05
     disbelief
    -0.05
    .Unicode
    -0.05
    POSITIVE LOGITS
    .scalablytyped
    0.08
    ustin
    0.08
    uju
    0.07
    nish
    0.07
    abile
    0.07
    ustria
    0.07
    ibly
    0.07
    arrera
    0.07
    iable
    0.07
    ODB
    0.07
    Activations Density 0.009%

    No Known Activations