© 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. 15-LLAMASCOPE-RES-131K
    11. 103926
    Prev
    Next
    INDEX
    Explanations

    issues related to prison conditions and human rights violations

    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
    ĶåĽŀ
    -0.10
    iyat
    -0.09
    quier
    -0.09
    ãĥ³ãĤº
    -0.09
    ÑģÑĤÑĢÑĥ
    -0.09
    agner
    -0.08
    bett
    -0.08
    zı
    -0.08
    iliz
    -0.08
    utow
    -0.08
    POSITIVE LOGITS
    0
    0.07
    2
    0.06
     spor
    0.06
    3
    0.06
     nor
    0.06
    4
    0.06
    0.06
    1
    0.06
    ch
    0.06
    ↵
    0.05
    Activations Density 0.001%

    No Known Activations