© 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. 15-LLAMASCOPE-RES-131K
    11. 855
    Prev
    Next
    INDEX
    Explanations

    terms related to network interfaces and their attributes

    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
    LIK
    -0.07
    ovit
    -0.07
     Glo
    -0.07
    loys
    -0.07
    roi
    -0.06
    lesc
    -0.06
     ÐļÑĢи
    -0.06
     otherwise
    -0.06
    æ´¥
    -0.06
    ucht
    -0.06
    POSITIVE LOGITS
    abay
    0.07
    bam
    0.06
    å¼
    0.06
    mates
    0.06
     Belmont
    0.06
    å°
    0.06
     ghi
    0.06
    èĩªèº«
    0.06
    iw
    0.06
    uba
    0.06
    Activations Density 0.020%

    No Known Activations