© 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. 60742
    Prev
    Next
    INDEX
    Explanations

    references to governmental reporting and advisory processes

    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
     å²
    -0.07
    å¾
    -0.07
     éŁ
    -0.06
    iese
    -0.06
     nev
    -0.06
    egie
    -0.06
    enties
    -0.06
     Arn
    -0.06
    ãĥªãĤ«
    -0.06
    пÑĢимеÑĢ
    -0.06
    POSITIVE LOGITS
     Congress
    0.09
     parliament
    0.07
    atto
    0.07
     Parliament
    0.07
    tach
    0.07
    ãĥ£
    0.07
    IDD
    0.07
     legislature
    0.06
    /framework
    0.06
     congress
    0.06
    Activations Density 0.011%

    No Known Activations