© 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. 125969
    Prev
    Next
    INDEX
    Explanations

    references to XML and associated document structures

    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
     exact
    -0.06
    år
    -0.06
    .scroll
    -0.06
    çİĩ
    -0.06
     last
    -0.06
     Sas
    -0.06
    ival
    -0.06
     McGu
    -0.06
     Keller
    -0.06
    ed
    -0.05
    POSITIVE LOGITS
    vore
    0.08
    yntax
    0.07
    deniz
    0.07
    rika
    0.07
    uede
    0.07
    tures
    0.07
    ettings
    0.07
    ike
    0.06
    antar
    0.06
    agination
    0.06
    Activations Density 0.006%

    No Known Activations