© 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. 130893
    Prev
    Next
    INDEX
    Explanations

    phrases related to processes and actions associated with tasks or applications

    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
     when
    -0.06
    raith
    -0.06
     somehow
    -0.06
    dados
    -0.06
     pleasure
    -0.05
    ward
    -0.05
    VERS
    -0.05
     phys
    -0.05
     Rex
    -0.05
     according
    -0.05
    POSITIVE LOGITS
     DISCLAIM
    0.08
    ÅĽcie
    0.07
    .scalablytyped
    0.07
    -ts
    0.07
     Sesso
    0.07
    oler
    0.07
    enburg
    0.07
    аÑİ
    0.07
    _Tick
    0.07
    ãĥ³ãĥĸ
    0.07
    Activations Density 0.004%

    No Known Activations