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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 95506
    Prev
    Next
    INDEX
    Explanations

    references to geographical locations and political entities

    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
    lam
    -0.06
     Lam
    -0.06
     Lamar
    -0.06
     lam
    -0.06
    kowski
    -0.05
    berman
    -0.05
    esters
    -0.05
    331
    -0.05
     ones
    -0.05
    ade
    -0.05
    POSITIVE LOGITS
    GLE
    0.08
    ãĥ³ãĤ¹
    0.07
    gle
    0.07
    _placement
    0.07
    \Builder
    0.07
    RIX
    0.07
    eof
    0.07
    .setViewport
    0.07
    ëħĦëıĦ
    0.07
    CTX
    0.07
    Activations Density 0.000%

    No Known Activations