© 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. 60951
    Prev
    Next
    INDEX
    Explanations

    URLs and links from online sources

    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
    e
    -0.06
    ĵĺ
    -0.06
    -
    -0.06
     Kaplan
    -0.06
     beg
    -0.06
    @hotmail
    -0.05
    -o
    -0.05
    ml
    -0.05
    ini
    -0.05
     NPR
    -0.05
    POSITIVE LOGITS
    ometr
    0.08
    ampo
    0.08
    iram
    0.07
     NEWS
    0.07
    aje
    0.07
    #ab
    0.07
    _cmos
    0.07
    /news
    0.07
    /tos
    0.07
    /jav
    0.07
    Activations Density 0.018%

    No Known Activations