© 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. 17-LLAMASCOPE-RES-131K
    11. 57268
    Prev
    Next
    INDEX
    Explanations

    references to hard drives and disk storage

    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
     íĿIJ
    -0.06
    .production
    -0.06
     Provid
    -0.06
    Patch
    -0.06
    uan
    -0.06
    ocoa
    -0.06
    esktop
    -0.06
    down
    -0.06
    caster
    -0.06
    ÑĢиÑĩ
    -0.06
    POSITIVE LOGITS
     storage
    0.08
     mount
    0.07
     drive
    0.07
     mounted
    0.07
    ace
    0.06
    -storage
    0.06
    mounted
    0.06
     disc
    0.06
     Mount
    0.06
    -mounted
    0.06
    Activations Density 0.022%

    No Known Activations