© 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. 105983
    Prev
    Next
    INDEX
    Explanations

    elements of programming code related to sorting algorithms

    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
    462
    -0.08
    IRD
    -0.06
    èij
    -0.06
    itti
    -0.06
    QM
    -0.06
    >Nama
    -0.06
    URN
    -0.06
    .metro
    -0.06
    ủ
    -0.06
    bject
    -0.06
    POSITIVE LOGITS
    ussed
    0.06
    åħ·
    0.06
    arend
    0.06
    aceous
    0.06
    Notify
    0.06
    adors
    0.06
    Ī
    0.05
    führt
    0.05
    orption
    0.05
    ä»ĭ
    0.05
    Activations Density 0.044%

    No Known Activations