© 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. 106083
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Posted" indicating posts or articles in a document

    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
    ãģ£ãģ¡
    -0.06
    eric
    -0.06
    914
    -0.06
     Emerson
    -0.06
    ago
    -0.06
    .Imp
    -0.06
     å·Ŀ
    -0.05
    ayo
    -0.05
    argent
    -0.05
    Desk
    -0.05
    POSITIVE LOGITS
    .toast
    0.07
    alia
    0.07
    abin
    0.07
     ìĤ¬ëŀĮìĿĢ
    0.07
    faction
    0.07
    ria
    0.07
    ÑįÑĤомÑĥ
    0.06
     Cosby
    0.06
    afs
    0.06
    -toggler
    0.06
    Activations Density 0.008%

    No Known Activations