© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 86941
    Prev
    Next
    INDEX
    Explanations

    discussions about the evolution of societal norms and expectations

    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
    ERSIST
    -0.07
    REFERRED
    -0.07
    DonaldTrump
    -0.07
    åį·
    -0.07
    ANTE
    -0.07
    agara
    -0.07
    isks
    -0.06
    _exempt
    -0.06
    격
    -0.06
    lü
    -0.06
    POSITIVE LOGITS
     finally
    0.08
     slowly
    0.08
     awareness
    0.08
    slow
    0.08
    finally
    0.07
     gradually
    0.07
    è¶Ĭ
    0.07
     generation
    0.07
    æħ¢
    0.07
    Slow
    0.06
    Activations Density 0.036%

    No Known Activations