© 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. 15-LLAMASCOPE-RES-131K
    11. 931
    Prev
    Next
    INDEX
    Explanations

    demonstrative pronouns and phrases indicating emphasis or importance

    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
     Merry
    -0.07
    ÄĻ
    -0.07
    onders
    -0.07
    pus
    -0.06
     Calder
    -0.06
    ANDING
    -0.06
    ÅĻil
    -0.06
    CAF
    -0.06
    idences
    -0.06
    'gc
    -0.06
    POSITIVE LOGITS
    okino
    0.07
    obi
    0.07
     mean
    0.06
     Means
    0.06
    640
    0.06
    ERVER
    0.06
     fact
    0.06
     Grove
    0.06
    xFB
    0.06
    usta
    0.06
    Activations Density 0.028%

    No Known Activations