© 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. 92173
    Prev
    Next
    INDEX
    Explanations

    names of individuals, characters, or entities associated with various themes or events

    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
    ÙĪاء
    -0.07
    ertz
    -0.07
    cie
    -0.07
    ãĥ³ãĥij
    -0.07
    ÑģÑıÑĤ
    -0.07
    ilos
    -0.07
    èľľ
    -0.07
    annes
    -0.07
     ÑĢÑĥками
    -0.07
    341
    -0.06
    POSITIVE LOGITS
     prominently
    0.10
     sebagai
    0.07
     alongside
    0.07
     among
    0.06
    uda
    0.06
     exclusively
    0.06
    apan
    0.06
     as
    0.06
    acks
    0.06
    enz
    0.06
    Activations Density 0.041%

    No Known Activations