© 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 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. 86230
    Prev
    Next
    INDEX
    Explanations

    references to inclusivity and eligibility criteria for accessing programs or services

    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
    ån
    -0.08
    odon
    -0.07
    ecure
    -0.07
    ायन
    -0.07
    ceae
    -0.06
     NSLocalizedString
    -0.06
    zie
    -0.06
     VÅ¡ech
    -0.06
    å¸Ń
    -0.06
    หาย
    -0.06
    POSITIVE LOGITS
     interested
    0.09
     Interested
    0.08
     interest
    0.08
     Anyone
    0.07
     anyone
    0.07
     anytime
    0.07
     compatible
    0.07
    Interested
    0.07
    :Any
    0.06
     Tong
    0.06
    Activations Density 0.016%

    No Known Activations