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. 29077
    Prev
    Next
    INDEX
    Explanations

    references to requirements and conditions

    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
    kart
    -0.08
    eli
    -0.06
     пÑĢедваÑĢ
    -0.06
    ãĥ©ãĤ¹
    -0.06
    nova
    -0.06
    oli
    -0.06
    _unset
    -0.06
    Ĵáŀ
    -0.06
     latest
    -0.06
     íĨµíķ©
    -0.06
    POSITIVE LOGITS
     subsequent
    0.17
     thereafter
    0.15
     subsequently
    0.15
     afterwards
    0.14
     next
    0.14
     then
    0.13
     ansch
    0.12
     afterward
    0.12
     THEN
    0.12
     later
    0.11
    Activations Density 0.008%

    No Known Activations