© 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. 3371
    Prev
    Next
    INDEX
    Explanations

    numerical values and counts 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
    ttp
    -0.07
    дÑı
    -0.07
    ottes
    -0.07
     Dialogue
    -0.06
    zone
    -0.06
    perator
    -0.06
    621
    -0.06
    iaux
    -0.06
    вай
    -0.06
     باÙĤ
    -0.06
    POSITIVE LOGITS
    nore
    0.07
    nul
    0.06
    elden
    0.06
    nock
    0.06
    ombat
    0.06
    odium
    0.06
    еÑĢи
    0.06
    #ad
    0.06
    pez
    0.06
     duration
    0.06
    Activations Density 0.010%

    No Known Activations