© 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. 79055
    Prev
    Next
    INDEX
    Explanations

    references to news stories or significant events

    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
    atar
    -0.06
    ual
    -0.06
    scribe
    -0.06
     Authority
    -0.06
     loss
    -0.06
    erm
    -0.05
    ammad
    -0.05
    implify
    -0.05
    .cn
    -0.05
    olve
    -0.05
    POSITIVE LOGITS
    364
    0.08
    лини
    0.07
    alama
    0.07
    opoulos
    0.07
    abcdefghijklmnop
    0.07
    ì°°
    0.07
    OfFile
    0.07
     пÑĥ
    0.07
     lat
    0.06
    utow
    0.06
    Activations Density 0.000%

    No Known Activations