© 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. 17-LLAMASCOPE-RES-131K
    6. 87097
    Prev
    Next
    INDEX
    Explanations

    dialogue or speech patterns in a narrative context

    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
     kamp
    -0.07
     camps
    -0.07
    ullan
    -0.06
    ContentSize
    -0.06
    uhan
    -0.06
    ufen
    -0.06
    SEC
    -0.06
    zung
    -0.06
    ilis
    -0.06
    azole
    -0.06
    POSITIVE LOGITS
    forth
    0.07
     reply
    0.07
     ëĮĢëĭµ
    0.07
     Eigen
    0.07
     replied
    0.07
     answer
    0.07
    reply
    0.06
     forth
    0.06
    Markup
    0.06
     bedtime
    0.06
    Activations Density 0.003%

    No Known Activations