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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 5569
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ÑĢÑı
    -0.07
    oyer
    -0.07
    rlen
    -0.06
    лаÑģÑĤи
    -0.06
    ald
    -0.06
    agher
    -0.06
    оÑĢоÑĤ
    -0.06
    iske
    -0.06
    uster
    -0.06
    ninger
    -0.06
    POSITIVE LOGITS
    enders
    0.08
    ending
    0.07
    ONS
    0.07
    ons
    0.07
    dou
    0.07
    ecz
    0.07
    eson
    0.07
    ello
    0.07
    bart
    0.06
     bar
    0.06
    Activations Density 0.002%

    No Known Activations