© 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. 58916
    Prev
    Next
    INDEX
    Explanations

    specific details and instructions related to appointments and documentation processes

    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
     Jar
    -0.07
    jar
    -0.06
    ume
    -0.06
    741
    -0.06
     jar
    -0.06
     primary
    -0.06
    anni
    -0.06
    ause
    -0.05
     unf
    -0.05
    ABEL
    -0.05
    POSITIVE LOGITS
    TestId
    0.08
    WithPath
    0.07
    ambre
    0.07
    RunWith
    0.07
    fee
    0.06
     kurs
    0.06
    IMATE
    0.06
    gamber
    0.06
     Sunder
    0.06
    venue
    0.06
    Activations Density 0.007%

    No Known Activations