© 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. 17-LLAMASCOPE-RES-131K
    11. 57068
    Prev
    Next
    INDEX
    Explanations

    references to animated music videos, particularly those related to classic songs

    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
    åĨ
    -0.07
    $:
    -0.07
    egin
    -0.06
    .connector
    -0.06
     Hindered
    -0.06
    ican
    -0.06
     Vig
    -0.06
    URNS
    -0.06
     Twice
    -0.06
    616
    -0.06
    POSITIVE LOGITS
    Instr
    0.06
    ationship
    0.06
    lt
    0.06
    rit
    0.06
    zelf
    0.06
    æ±Ĺ
    0.06
    outu
    0.06
    arkan
    0.06
    mos
    0.06
    ufac
    0.06
    Activations Density 0.001%

    No Known Activations