© 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. 82594
    Prev
    Next
    INDEX
    Explanations

    phrases related to teaching and guidance

    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
    ëĿ½
    -0.07
    497
    -0.07
    avra
    -0.07
    felt
    -0.07
    ancias
    -0.07
    iod
    -0.06
     Vor
    -0.06
     hammer
    -0.06
    eme
    -0.06
     ability
    -0.06
    POSITIVE LOGITS
     how
    0.10
    rys
    0.07
     cómo
    0.07
    æĢİ
    0.07
    Ñģи
    0.07
     ÙĥÙĬÙģ
    0.07
    how
    0.07
    å¦Ĥä½ķ
    0.06
    148
    0.06
     technique
    0.06
    Activations Density 0.013%

    No Known Activations