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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 95002
    Prev
    Next
    INDEX
    Explanations

    negative terms or phrases indicating the absence or failure of something

    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
    ίοÏĤ
    -0.07
    zeit
    -0.06
    rod
    -0.06
    ncia
    -0.06
    UNCTION
    -0.06
    holding
    -0.06
     Dro
    -0.06
    halt
    -0.06
    iously
    -0.06
    .DropTable
    -0.06
    POSITIVE LOGITS
    rica
    0.07
    ark
    0.07
    ABCDE
    0.06
    cu
    0.06
    tres
    0.06
    cum
    0.06
    orage
    0.06
    rier
    0.06
    acco
    0.06
    _si
    0.06
    Activations Density 0.025%

    No Known Activations