© 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. 85990
    Prev
    Next
    INDEX
    Explanations

    identifiers and metadata in programming or documentation contexts

    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
    anes
    -0.07
    istrate
    -0.07
    agn
    -0.06
    atz
    -0.06
     Cler
    -0.06
    onna
    -0.06
    erge
    -0.06
     Dem
    -0.06
     beard
    -0.06
    ARAM
    -0.06
    POSITIVE LOGITS
    -comments
    0.07
    Reviewer
    0.07
     serialVersionUID
    0.07
     puta
    0.06
    icontrol
    0.06
    .scalablytyped
    0.06
    rippling
    0.06
    ottes
    0.06
    ERM
    0.06
     Thrones
    0.06
    Activations Density 0.002%

    No Known Activations