© 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. 3587
    Prev
    Next
    INDEX
    Explanations

    geographic names and terms related to countries and regions

    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
    irsch
    -0.09
    AS
    -0.07
     AS
    -0.07
    asia
    -0.07
    ASK
    -0.07
     eros
    -0.07
    ERSION
    -0.07
    еÑĢÑĪ
    -0.07
    ASC
    -0.07
     ASC
    -0.07
    POSITIVE LOGITS
    ival
    0.08
     AWS
    0.07
     CWE
    0.06
    oy
    0.06
    ivated
    0.06
    Bay
    0.06
    atto
    0.06
    ivalent
    0.06
    Chain
    0.06
     Cow
    0.06
    Activations Density 0.047%

    No Known Activations