© 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. 17-LLAMASCOPE-RES-131K
    11. 69709
    Prev
    Next
    INDEX
    Explanations

    references to availability and conditions related to food and water resources

    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
     merc
    -0.06
     ego
    -0.06
    feit
    -0.06
    eniable
    -0.06
     Bris
    -0.06
     oral
    -0.06
    ä¹
    -0.06
    assy
    -0.06
     undesirable
    -0.06
    asi
    -0.06
    POSITIVE LOGITS
    inci
    0.07
    èĮĤ
    0.07
    ัà¸ĵà¸ij
    0.07
    plode
    0.07
    uet
    0.07
     distributed
    0.07
    iland
    0.07
     Distributed
    0.07
    hr
    0.07
    iar
    0.07
    Activations Density 0.082%

    No Known Activations