© 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. 79523
    Prev
    Next
    INDEX
    Explanations

    instances of the word "ne" and its variations, indicating a focus on nouns or terms related to names or identity

    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
    ança
    -0.07
    unct
    -0.07
    rawer
    -0.06
     обÑĬ
    -0.06
    pei
    -0.06
    avn
    -0.06
    uld
    -0.06
    urs
    -0.06
    oke
    -0.06
    stru
    -0.06
    POSITIVE LOGITS
    isser
    0.08
    /ne
    0.07
    esse
    0.07
    emiah
    0.07
    plode
    0.07
    ptune
    0.07
    anche
    0.07
    pra
    0.07
    cdf
    0.07
    Äįas
    0.07
    Activations Density 0.017%

    No Known Activations