© 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. 84166
    Prev
    Next
    INDEX
    Explanations

    occurrences of the preposition "on."

    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
    .SDK
    -0.07
     Dog
    -0.07
    Dog
    -0.07
     dog
    -0.06
     é¤
    -0.06
     autof
    -0.06
     cre
    -0.06
    ietf
    -0.06
    orizontal
    -0.06
    ãĥĥãĥģ
    -0.06
    POSITIVE LOGITS
    bourg
    0.07
    ocz
    0.07
    urgeon
    0.07
    homepage
    0.06
     Bauer
    0.06
    aton
    0.06
    âĢĮØ´ÙĨ
    0.06
    岡
    0.06
    ken
    0.06
    Äįe
    0.06
    Activations Density 0.012%

    No Known Activations