© 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. 17-LLAMASCOPE-RES-131K
    6. 55980
    Prev
    Next
    INDEX
    Explanations

    expressions of emotional states related to feeling and perception

    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
    ãĥĥãĤ¯
    -0.08
    ãĥĢãĤ¤
    -0.07
    OTAL
    -0.07
    uzzi
    -0.07
    маз
    -0.07
    алеж
    -0.07
    ̣
    -0.07
    RowCount
    -0.07
    azar
    -0.06
    ç¥Ŀ
    -0.06
    POSITIVE LOGITS
    user
    0.06
     Cave
    0.06
     Lair
    0.06
     crossorigin
    0.06
    uman
    0.06
    /us
    0.06
    rier
    0.06
    utherford
    0.06
    çª
    0.06
    age
    0.06
    Activations Density 0.012%

    No Known Activations