© 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. 16240
    Prev
    Next
    INDEX
    Explanations

    locations or contexts within the text

    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
     a
    -0.07
    a
    -0.07
     an
    -0.06
    yn
    -0.06
    ither
    -0.06
    ansa
    -0.06
     enough
    -0.06
    STEM
    -0.06
     alike
    -0.06
     something
    -0.06
    POSITIVE LOGITS
    pector
    0.08
    liest
    0.08
    ân
    0.07
    ighest
    0.07
    κÏĦη
    0.07
    .openConnection
    0.07
     cui
    0.07
    LastError
    0.07
    amet
    0.07
     któ
    0.07
    Activations Density 0.253%

    No Known Activations