Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 87396
    Prev
    Next
    INDEX
    Explanations

    references to well-known brands and companies

    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
    aaaaaaaa
    -0.08
    servername
    -0.07
    OrDefault
    -0.07
    aaaa
    -0.06
    ладÑĥ
    -0.06
     ï¼Ī
    -0.06
    воÑİ
    -0.06
    errated
    -0.06
    edium
    -0.06
    ffer
    -0.06
    POSITIVE LOGITS
     amongst
    0.08
     FindObjectOfType
    0.07
    aylight
    0.07
     among
    0.07
    obox
    0.06
    Ñī
    0.06
    429
    0.06
     etc
    0.06
    ReadWrite
    0.06
    atts
    0.06
    Activations Density 0.017%

    No Known Activations