Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 16384
    Prev
    Next
    INDEX
    Explanations

    references to human interactions and dialogues

    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
    senal
    -0.09
    åĨµ
    -0.09
    alink
    -0.09
    ême
    -0.08
    quee
    -0.08
    alim
    -0.08
     CHARSET
    -0.08
    iox
    -0.07
    lém
    -0.07
    bia
    -0.07
    POSITIVE LOGITS
     reply
    0.13
     response
    0.10
     replied
    0.10
     replies
    0.10
     then
    0.09
     respond
    0.09
     Reply
    0.09
    reply
    0.09
     responds
    0.08
     responses
    0.08
    Activations Density 0.034%

    No Known Activations