© 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. 17-LLAMASCOPE-RES-131K
    11. 60242
    Prev
    Next
    INDEX
    Explanations

    comparative expressions indicating superiority or preference

    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
    ë²Į
    -0.07
    anium
    -0.07
     há»į
    -0.06
    .handleClick
    -0.06
    esktop
    -0.06
    ingga
    -0.06
    าà¸ĩ
    -0.06
    TOTYPE
    -0.06
     chứ
    -0.06
    Ñĥже
    -0.06
    POSITIVE LOGITS
     other
    0.10
     any
    0.10
     having
    0.09
     alternatives
    0.09
     alternative
    0.08
     simply
    0.07
     anything
    0.07
     altern
    0.07
     ones
    0.07
     continued
    0.07
    Activations Density 0.022%

    No Known Activations