© 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. 126130
    Prev
    Next
    INDEX
    Explanations

    phrases indicating authorship or attribution

    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
    etter
    -0.08
    _Tis
    -0.07
    .LayoutStyle
    -0.07
    ekil
    -0.07
    seealso
    -0.07
    gaard
    -0.07
    _tF
    -0.07
    IRR
    -0.07
    _mE
    -0.07
    _Pods
    -0.07
    POSITIVE LOGITS
     several
    0.08
     the
    0.07
     two
    0.07
     authorities
    0.07
     various
    0.06
    lef
    0.06
     both
    0.06
    opup
    0.06
    lu
    0.06
    avad
    0.06
    Activations Density 0.026%

    No Known Activations