© 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. 15-LLAMASCOPE-RES-131K
    11. 27122
    Prev
    Next
    INDEX
    Explanations

    punctuation and formatting marks in the text

    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
    äs
    -0.08
    .spin
    -0.07
     dialect
    -0.07
    å¡ļ
    -0.06
     Parad
    -0.06
     Dial
    -0.06
    ilter
    -0.06
    uby
    -0.06
    ô
    -0.06
    raith
    -0.06
    POSITIVE LOGITS
    ;element
    0.07
     schn
    0.07
    ADOW
    0.06
    ellers
    0.06
    /renderer
    0.06
    clin
    0.06
     barr
    0.06
    0.06
    ãĥ«ãĥķ
    0.06
    à¸Ńว
    0.05
    Activations Density 0.002%

    No Known Activations