© 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. 9-LLAMASCOPE-RES-131K
    11. 96735
    Prev
    Next
    INDEX
    Explanations

    names of artists or performers, particularly in a musical context

    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
    igli
    -0.07
    achi
    -0.07
    inois
    -0.07
    inee
    -0.06
    esta
    -0.06
    emens
    -0.06
    RT
    -0.06
    ãĥĥãĥģ
    -0.06
    zd
    -0.06
    PG
    -0.06
    POSITIVE LOGITS
    okino
    0.07
    loat
    0.07
    acente
    0.07
    etooth
    0.06
    IZER
    0.06
     migrationBuilder
    0.06
    rox
    0.06
    LINK
    0.06
    LIK
    0.06
    &p
    0.06
    Activations Density 0.003%

    No Known Activations