© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 4307
    Prev
    Next
    INDEX
    Explanations

    phrases indicating concepts, ideas, or experiences that are difficult or impossible to fully comprehend

    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
    eyJ
    -0.08
     :↵↵↵↵
    -0.07
    ZW
    -0.07
    (æľ¨
    -0.07
    enek
    -0.07
    utow
    -0.07
    .rar
    -0.07
    ataire
    -0.07
    fillType
    -0.07
    kili
    -0.06
    POSITIVE LOGITS
     repro
    0.10
     dispute
    0.09
     anything
    0.09
     repair
    0.09
     belief
    0.09
     anyone
    0.08
     comprehension
    0.08
     compare
    0.08
     any
    0.07
     reach
    0.07
    Activations Density 0.005%

    No Known Activations