© 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. 106290
    Prev
    Next
    INDEX
    Explanations

    terms related to rankings and ratings for various subjects

    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
    eut
    -0.08
    ulle
    -0.08
    ewan
    -0.07
    unj
    -0.07
    onian
    -0.07
    ezi
    -0.06
    /from
    -0.06
    orks
    -0.06
    ÑĢез
    -0.06
    fh
    -0.06
    POSITIVE LOGITS
    enance
    0.08
     among
    0.08
     sebagai
    0.07
     amongst
    0.07
    iate
    0.07
    ixin
    0.07
     sobie
    0.07
    Charsets
    0.07
    etrize
    0.06
     Ñģобой
    0.06
    Activations Density 0.010%

    No Known Activations