© 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. 31128
    Prev
    Next
    INDEX
    Explanations

    the presence of the character "Ñij" in various contexts

    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
     Mug
    -0.07
    ÑģÑĮ
    -0.07
    MOTE
    -0.07
    yy
    -0.07
    ided
    -0.06
    culate
    -0.06
    anded
    -0.06
    untu
    -0.06
    vette
    -0.06
     endwhile
    -0.06
    POSITIVE LOGITS
    ear
    0.07
    ingt
    0.07
    hip
    0.07
    stateParams
    0.06
    hem
    0.06
    ÅĻi
    0.06
    lx
    0.06
    era
    0.06
    ÙĦ
    0.06
    mers
    0.06
    Activations Density 0.005%

    No Known Activations