Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 5747
    Prev
    Next
    INDEX
    Explanations

    terms related to data backup and database management

    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
     вб
    -0.07
    'http
    -0.07
    asher
    -0.07
    811
    -0.07
    بÙĬÙĨ
    -0.07
    "http
    -0.07
     div
    -0.07
    Supply
    -0.06
    erez
    -0.06
    ç«
    -0.06
    POSITIVE LOGITS
     backup
    0.15
     backing
    0.14
     Backup
    0.13
     backed
    0.13
    backup
    0.12
    Backup
    0.12
     backups
    0.12
     restore
    0.11
    .backup
    0.11
    Backing
    0.10
    Activations Density 0.022%

    No Known Activations