© 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. 5-LLAMASCOPE-RES-131K
    11. 126419
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly quotation marks and semicolons

    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
     Rear
    -0.07
    re
    -0.07
    woord
    -0.07
    iest
    -0.06
    bw
    -0.06
    idar
    -0.06
    rear
    -0.06
    thing
    -0.06
    poke
    -0.06
     Ort
    -0.06
    POSITIVE LOGITS
    è¡ĵ
    0.07
     consult
    0.06
    Canonical
    0.06
    -pagination
    0.06
     Phill
    0.06
    Ñŀ
    0.06
    umer
    0.06
    consult
    0.06
    BlockSize
    0.06
    ç£
    0.06
    Activations Density 0.001%

    No Known Activations