© 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. 9-LLAMASCOPE-RES-131K
    11. 95688
    Prev
    Next
    INDEX
    Explanations

    expressions of emotions and engagement in activities

    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
    anzi
    -0.07
    uzzle
    -0.07
    angu
    -0.07
    oton
    -0.07
    retty
    -0.07
    permalink
    -0.07
    анÑĤа
    -0.07
    ilst
    -0.06
    ContentSize
    -0.06
    ilter
    -0.06
    POSITIVE LOGITS
    (éĩij
    0.06
    celik
    0.06
     شع
    0.06
    nie
    0.06
     cocks
    0.05
    ÑĮе
    0.05
    tails
    0.05
    çĿ
    0.05
    318
    0.05
    oda
    0.05
    Activations Density 0.001%

    No Known Activations