© 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. 126020
    Prev
    Next
    INDEX
    Explanations

    concepts related to scientific measurements and engineering properties

    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
    -eyed
    -0.07
    odable
    -0.07
    ullet
    -0.07
    važ
    -0.07
    argest
    -0.07
    ideon
    -0.07
    iqueta
    -0.07
    λεκ
    -0.07
     ErrorMessage
    -0.06
    CHAT
    -0.06
    POSITIVE LOGITS
    /high
    0.17
    -low
    0.13
    -high
    0.10
    ãĢģé«ĺ
    0.09
    (high
    0.07
    aged
    0.07
    high
    0.06
    udded
    0.06
    /value
    0.06
     cao
    0.06
    Activations Density 0.075%

    No Known Activations