© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 70823
    Prev
    Next
    INDEX
    Explanations

    phrases related to recommendations and reviews

    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
     EVE
    -0.07
    warz
    -0.06
     Hust
    -0.06
    creds
    -0.06
    ÑĮÑĤе
    -0.06
    uan
    -0.06
     guts
    -0.06
     tend
    -0.06
    æľ¯
    -0.06
    ored
    -0.06
    POSITIVE LOGITS
    ãģĵãĤį
    0.07
    etail
    0.07
    ampa
    0.07
    κλη
    0.07
     Mic
    0.07
     Sür
    0.07
     DISCLAIM
    0.07
     Juda
    0.07
    Mic
    0.06
    ITHER
    0.06
    Activations Density 0.003%

    No Known Activations