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. 84219
    Prev
    Next
    INDEX
    Explanations

    references to scientific organizations and funding information

    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
     dign
    -0.06
    adiens
    -0.06
     caus
    -0.06
    Įĵ
    -0.06
    omez
    -0.06
     Revelation
    -0.05
    okol
    -0.05
    obus
    -0.05
    obar
    -0.05
     Oliv
    -0.05
    POSITIVE LOGITS
     NSF
    0.10
    kest
    0.09
    .si
    0.07
    agrant
    0.07
     Lyon
    0.07
    (NS
    0.07
    .Restr
    0.07
    stroy
    0.07
     ÑģÑĤан
    0.07
    adro
    0.06
    Activations Density 0.014%

    No Known Activations