© 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. 117382
    Prev
    Next
    INDEX
    Explanations

    phrases indicating partnerships or affiliations

    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
    ARB
    -0.07
    tam
    -0.06
    isel
    -0.06
    grave
    -0.06
    Spark
    -0.06
    etre
    -0.06
    ãĥģãĥ¥
    -0.06
    ÑĨеп
    -0.06
    ARP
    -0.06
    grav
    -0.06
    POSITIVE LOGITS
     Dit
    0.27
     Likewise
    0.27
     likewise
    0.25
     same
    0.25
     similarly
    0.24
     Similarly
    0.24
    Similarly
    0.23
    Lik
    0.23
    same
    0.22
     dit
    0.22
    Activations Density 0.213%

    No Known Activations