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. 119240
    Prev
    Next
    INDEX
    Explanations

    references to academic publication guidelines and ethics

    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
    AIL
    -0.07
    ail
    -0.07
    avin
    -0.06
     cr
    -0.06
    azon
    -0.06
    rek
    -0.06
    reh
    -0.06
     wind
    -0.06
     chrom
    -0.06
     cert
    -0.05
    POSITIVE LOGITS
     submission
    0.10
    submission
    0.09
     Submission
    0.09
    SetBranch
    0.08
     submissions
    0.08
    تÙħر
    0.08
     TEMPLATE
    0.08
     æĬķ稿
    0.08
    Submitting
    0.08
     submitting
    0.08
    Activations Density 0.008%

    No Known Activations