© 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. 87399
    Prev
    Next
    INDEX
    Explanations

    proper nouns and references to specific schools or conferences

    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
    çĻ»
    -0.06
     INC
    -0.06
     foreigners
    -0.06
    osto
    -0.06
    azor
    -0.06
     usually
    -0.06
     abroad
    -0.05
    ви
    -0.05
    nier
    -0.05
     vfs
    -0.05
    POSITIVE LOGITS
    Enlarge
    0.07
    ãĥ³ãĤ°ãĥ«
    0.07
     teh
    0.07
    оваÑĢи
    0.07
    ibal
    0.07
     sez
    0.07
    eree
    0.07
     grille
    0.06
    onte
    0.06
    ÑĢаÑĤно
    0.06
    Activations Density 0.000%

    No Known Activations