© 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. 76147
    Prev
    Next
    INDEX
    Explanations

    concerns about potential negative outcomes and risks

    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
    ober
    -0.07
    _probability
    -0.07
    еÑĢп
    -0.07
    oden
    -0.07
    jedn
    -0.07
    íĻĺ
    -0.07
    ãĥ³ãĥĩ
    -0.07
    iloc
    -0.07
    ivor
    -0.06
    ëĮĢìĿĺ
    -0.06
    POSITIVE LOGITS
     too
    0.12
     might
    0.12
    might
    0.11
     TOO
    0.11
    too
    0.10
     Might
    0.10
    太
    0.09
     Too
    0.08
    -too
    0.08
    Too
    0.08
    Activations Density 0.043%

    No Known Activations