© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 94887
    Prev
    Next
    INDEX
    Explanations

    terms associated with requirements and validation

    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
    qui
    -0.07
    RIORITY
    -0.07
     dope
    -0.07
    ug
    -0.06
    esto
    -0.06
    agar
    -0.06
    variably
    -0.06
    enu
    -0.06
    fully
    -0.06
    antar
    -0.06
    POSITIVE LOGITS
    Ùĥس
    0.07
     èĢ
    0.07
    ombres
    0.06
    imap
    0.06
    nant
    0.06
    amber
    0.06
    acier
    0.06
    евеÑĢ
    0.06
    illac
    0.06
    urdy
    0.06
    Activations Density 0.012%

    No Known Activations