© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 5-LLAMASCOPE-RES-131K
    11. 126553
    Prev
    Next
    INDEX
    Explanations

    numerical data, particularly related to identification or tracking codes

    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
    621
    -0.08
    ousel
    -0.07
    DTV
    -0.06
    olla
    -0.06
     Fargo
    -0.06
    /rss
    -0.06
    avid
    -0.05
     layered
    -0.05
    ilar
    -0.05
    acher
    -0.05
    POSITIVE LOGITS
    ekim
    0.07
    Scrollbar
    0.07
    HEMA
    0.07
     nouve
    0.07
    èm
    0.07
    .accept
    0.07
    bild
    0.06
     %[
    0.06
    .asm
    0.06
    .staff
    0.06
    Activations Density 0.049%

    No Known Activations