© 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. 82747
    Prev
    Next
    INDEX
    Explanations

    occurrences of specific letters or characters in words, particularly focusing on ones with the letter "z"

    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
    atically
    -0.06
    ihu
    -0.06
     rfl
    -0.06
    559
    -0.06
    ification
    -0.06
     bom
    -0.06
     apl
    -0.06
    inkel
    -0.06
     Bid
    -0.06
    -0.06
    POSITIVE LOGITS
    cano
    0.07
    Parms
    0.07
    REEN
    0.07
     münchen
    0.07
     öden
    0.07
    xs
    0.07
    ASA
    0.06
    serter
    0.06
    ovÃŃ
    0.06
     gross
    0.06
    Activations Density 0.016%

    No Known Activations