© 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. 17-LLAMASCOPE-RES-131K
    11. 117123
    Prev
    Next
    INDEX
    Explanations

    details about characteristics and uniqueness of individuals or entities

    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
    icult
    -0.06
    üns
    -0.06
    706
    -0.06
    zim
    -0.06
    onde
    -0.06
     option
    -0.06
    option
    -0.06
    ån
    -0.05
    eba
    -0.05
     Mutual
    -0.05
    POSITIVE LOGITS
     unusual
    0.18
     special
    0.16
     unique
    0.15
    çī¹æ®Ĭ
    0.15
     uniqueness
    0.14
    (unique
    0.14
    special
    0.13
     Unique
    0.13
     abnormal
    0.13
    unique
    0.13
    Activations Density 0.046%

    No Known Activations