© 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. 126034
    Prev
    Next
    INDEX
    Explanations

    references to elevation and emotional intensity

    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
    casts
    -0.06
     fix
    -0.06
     Pew
    -0.06
    oin
    -0.06
     spo
    -0.05
     Mrs
    -0.05
     view
    -0.05
    riet
    -0.05
     catalyst
    -0.05
    UDENT
    -0.05
    POSITIVE LOGITS
     ante
    0.13
     stakes
    0.11
     level
    0.09
     levels
    0.09
     dial
    0.09
    level
    0.09
    iginal
    0.08
    plevel
    0.08
     LEVEL
    0.08
    Level
    0.08
    Activations Density 0.050%

    No Known Activations