© 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. 55402
    Prev
    Next
    INDEX
    Explanations

    instances of comment sections in articles or posts

    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
    úi
    -0.07
    contri
    -0.07
    बर
    -0.07
    ROWS
    -0.06
    anted
    -0.06
     frank
    -0.06
    DDD
    -0.06
    311
    -0.06
     окÑĤ
    -0.06
    claim
    -0.06
    POSITIVE LOGITS
    mann
    0.08
    ient
    0.06
     on
    0.06
     Affero
    0.06
    p
    0.06
     upon
    0.06
    aux
    0.06
    agn
    0.06
    ebek
    0.06
    eless
    0.06
    Activations Density 0.000%

    No Known Activations