© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 95533
    Prev
    Next
    INDEX
    Explanations

    references to file names and file handling operations

    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
    ãĤ¥
    -0.06
     sight
    -0.06
    itz
    -0.06
    anic
    -0.06
    een
    -0.06
     possibility
    -0.06
    minster
    -0.06
    enta
    -0.05
     against
    -0.05
     finish
    -0.05
    POSITIVE LOGITS
    ر
    0.08
    /filepath
    0.08
    stants
    0.08
    LOCKS
    0.07
    washer
    0.07
    preh
    0.07
    krit
    0.07
    rupa
    0.07
    rush
    0.07
    ipse
    0.07
    Activations Density 0.008%

    No Known Activations