© 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. 106317
    Prev
    Next
    INDEX
    Explanations

    code snippets involving variable assignments and method definitions

    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
    ói
    -0.07
    adir
    -0.07
    thon
    -0.07
    ocking
    -0.07
     пÑĢид
    -0.07
     Ú©Ø´
    -0.06
    blade
    -0.06
    ock
    -0.06
    κÏħ
    -0.06
    artz
    -0.06
    POSITIVE LOGITS
    eten
    0.07
    ħ§
    0.07
    atern
    0.06
     stringify
    0.06
    _ELEMENTS
    0.06
    InstanceOf
    0.06
    ìĭĿ
    0.06
    .fore
    0.06
    plied
    0.06
    ñana
    0.05
    Activations Density 0.004%

    No Known Activations