© 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. 29167
    Prev
    Next
    INDEX
    Explanations

    terms related to briefings and various types of instructional guides

    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
    виÑĤ
    -0.07
    ÐĬ
    -0.07
    /vendors
    -0.06
    fone
    -0.06
     ì§ģìłij
    -0.05
    ยà¸Ļà¸ķ
    -0.05
     enqu
    -0.05
     rost
    -0.05
    ,copy
    -0.05
     enf
    -0.05
    POSITIVE LOGITS
    -series
    0.09
     series
    0.08
     entitled
    0.08
    series
    0.08
    Äįel
    0.07
     titled
    0.07
     Series
    0.07
    queue
    0.07
    obl
    0.07
    apos
    0.07
    Activations Density 0.034%

    No Known Activations