© 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. 56363
    Prev
    Next
    INDEX
    Explanations

    instances of the word "discuss" and its variations

    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
    ãģĤ
    -0.07
    anas
    -0.07
    /full
    -0.07
    ux
    -0.07
    aras
    -0.07
    иком
    -0.07
    orris
    -0.07
    come
    -0.07
    одав
    -0.06
    urus
    -0.06
    POSITIVE LOGITS
    aire
    0.07
     whether
    0.07
     topics
    0.07
     matters
    0.07
    sek
    0.07
     how
    0.07
    ative
    0.07
    -about
    0.07
     about
    0.07
    æ¸ħæ¥ļ
    0.06
    Activations Density 0.022%

    No Known Activations