© 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. 9-LLAMASCOPE-RES-131K
    11. 95327
    Prev
    Next
    INDEX
    Explanations

    URLs or links to websites

    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
    c
    -0.07
    wel
    -0.07
    a
    -0.07
    vl
    -0.06
    i
    -0.06
    arry
    -0.06
    dao
    -0.06
    b
    -0.06
    w
    -0.06
     typ
    -0.06
    POSITIVE LOGITS
    ÑģÑĤÑĢо
    0.07
    θι
    0.07
    лин
    0.07
    atatype
    0.07
    iciones
    0.07
    ariant
    0.07
    StartPosition
    0.07
    kdir
    0.07
    embro
    0.06
    кеÑĤ
    0.06
    Activations Density 0.013%

    No Known Activations