© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 62065
    Prev
    Next
    INDEX
    Explanations

    conjunctions and phrases indicating connections or contrasts in arguments or narratives

    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
    rio
    -0.07
    557
    -0.06
    iek
    -0.06
     вÑĭпол
    -0.06
    getDisplay
    -0.06
    Ģìŀ¥
    -0.06
    _TLS
    -0.06
    é¨
    -0.06
     Trident
    -0.05
    .nlm
    -0.05
    POSITIVE LOGITS
     unless
    0.07
    unless
    0.07
     Arc
    0.07
    .hom
    0.07
     zatÃŃm
    0.07
    IVAL
    0.07
    ubat
    0.07
     nowhere
    0.07
     Playground
    0.07
    _CONTINUE
    0.07
    Activations Density 0.023%

    No Known Activations