© 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. 41117
    Prev
    Next
    INDEX
    Explanations

    numeric values related to data or statistics

    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
    erm
    -0.08
    evity
    -0.08
    olia
    -0.08
    ollo
    -0.08
    æ³Ĭ
    -0.07
    oure
    -0.07
    -cigaret
    -0.07
    γο
    -0.07
    amı
    -0.07
    edia
    -0.07
    POSITIVE LOGITS
    agli
    0.08
     pud
    0.06
    ordes
    0.06
    ãģĦãģ§
    0.06
    thetic
    0.06
    ãĤīãģı
    0.06
    ĻĤ
    0.05
    ereal
    0.05
    ud
    0.05
    .modified
    0.05
    Activations Density 0.021%

    No Known Activations