© 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. 17-LLAMASCOPE-RES-131K
    11. 82622
    Prev
    Next
    INDEX
    Explanations

    references and citations in academic or formal texts

    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
    stit
    -0.07
     ink
    -0.06
     Cent
    -0.06
     Nero
    -0.06
    Anchor
    -0.06
     and
    -0.05
     Dud
    -0.05
     S
    -0.05
     &
    -0.05
     Tro
    -0.05
    POSITIVE LOGITS
    dür
    0.08
    -AA
    0.07
    peed
    0.07
    cales
    0.07
    ÑĢÑĸд
    0.07
    ourced
    0.07
    fromJson
    0.07
    ÑĪкÑĥ
    0.07
    owitz
    0.07
    ãĤīãģĹ
    0.07
    Activations Density 0.001%

    No Known Activations