© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 94621
    Prev
    Next
    INDEX
    Explanations

    terms related to vocabulary or word classification systems

    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
    orks
    -0.07
    acket
    -0.06
    iggers
    -0.06
    acker
    -0.06
    eah
    -0.06
    y
    -0.06
    оÑģÑĤ
    -0.06
    ddl
    -0.06
    ,
    -0.06
    andez
    -0.05
    POSITIVE LOGITS
    arella
    0.08
     ActionTypes
    0.08
    vertisement
    0.08
    sci
    0.08
    ilitating
    0.07
    ility
    0.07
    ijn
    0.07
    ducted
    0.07
    summ
    0.07
    ìĹħ
    0.07
    Activations Density 0.000%

    No Known Activations