© 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. 29713
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal experiences and routine behaviors

    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
    slu
    -0.07
    TEGER
    -0.07
    ableOpacity
    -0.06
    bew
    -0.06
    buz
    -0.06
    ekk
    -0.06
    ket
    -0.06
    ä¸Ģ缴
    -0.06
    oration
    -0.06
    Ä°S
    -0.06
    POSITIVE LOGITS
    ìĶ©
    0.07
     someone
    0.07
     somebody
    0.07
     Zus
    0.07
     something
    0.07
    occ
    0.07
     Asked
    0.06
     Occ
    0.06
    Something
    0.06
    æľºä¼ļ
    0.06
    Activations Density 0.007%

    No Known Activations