© 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. 71558
    Prev
    Next
    INDEX
    Explanations

    instances of the word "let" used in various contexts

    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
    ordin
    -0.07
    aliz
    -0.06
    ieg
    -0.06
    .cg
    -0.06
    orden
    -0.06
    ria
    -0.06
    al
    -0.06
    verture
    -0.06
    rie
    -0.06
    portun
    -0.06
    POSITIVE LOGITS
     nor
    0.07
    ayıp
    0.07
    criptor
    0.07
    eways
    0.07
    DownList
    0.07
    ãĥ¬ãĥĥãĥĪ
    0.06
    igation
    0.06
    ovsky
    0.06
    ÑĢап
    0.06
     ÑĸменÑĸ
    0.06
    Activations Density 0.003%

    No Known Activations