© 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. 58818
    Prev
    Next
    INDEX
    Explanations

    pronouns that indicate subject or object reference

    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
    iph
    -0.07
    edis
    -0.07
    ynamo
    -0.06
    _flash
    -0.06
    帽
    -0.06
    uru
    -0.06
    ÂĨ
    -0.06
    Descricao
    -0.06
    yonel
    -0.06
    trand
    -0.06
    POSITIVE LOGITS
    nesc
    0.07
    ereum
    0.06
    å¶
    0.06
    haps
    0.06
    ksi
    0.06
    ivy
    0.06
    sti
    0.06
    еÑĪ
    0.06
    aug
    0.06
    UBL
    0.06
    Activations Density 0.002%

    No Known Activations