© 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. 71213
    Prev
    Next
    INDEX
    Explanations

    identifiers or codes associated with various methods and substances in scientific contexts

    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
    _,,
    -0.07
    _above
    -0.07
    iniz
    -0.07
    è¸
    -0.07
    amenti
    -0.06
    bilder
    -0.06
    odom
    -0.06
    imli
    -0.06
    utting
    -0.06
    inki
    -0.06
    POSITIVE LOGITS
     process
    0.06
    otr
    0.06
     own
    0.06
    achu
    0.05
    roit
    0.05
    IVA
    0.05
     humans
    0.05
    656
    0.05
    noop
    0.05
     NA
    0.05
    Activations Density 0.001%

    No Known Activations