© 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. 9-LLAMASCOPE-RES-131K
    11. 98055
    Prev
    Next
    INDEX
    Explanations

    occurrences of the name "Dominic Raab" and related identifiers

    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
     biased
    -0.07
     bias
    -0.07
    bias
    -0.07
    biased
    -0.06
    osto
    -0.06
    atör
    -0.06
    lem
    -0.06
    ech
    -0.06
    alth
    -0.06
    ija
    -0.06
    POSITIVE LOGITS
    OrNil
    0.06
     èĩªåĬ¨çĶŁæĪIJ
    0.06
    епÑĤи
    0.06
    inka
    0.06
    inke
    0.06
    779
    0.06
    ABCDEFGHI
    0.06
    emark
    0.06
    Nat
    0.06
    ãĥ³ãĥĸ
    0.06
    Activations Density 0.001%

    No Known Activations