© 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. 9-LLAMASCOPE-RES-131K
    11. 95640
    Prev
    Next
    INDEX
    Explanations

    time-related information in reports

    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
    ingu
    -0.07
    psilon
    -0.07
    ican
    -0.07
    898
    -0.07
    ica
    -0.07
    ÅĻila
    -0.07
    piel
    -0.06
    pton
    -0.06
    Ñħа
    -0.06
     Brewery
    -0.06
    POSITIVE LOGITS
    Twig
    0.06
     elev
    0.06
    umerator
    0.06
    ldr
    0.06
    ako
    0.06
    uien
    0.06
     bev
    0.05
    çĽĹ
    0.05
    coc
    0.05
    åŃĶ
    0.05
    Activations Density 0.001%

    No Known Activations