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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 4747
    Prev
    Next
    INDEX
    Explanations

    references to music albums and their 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
    ãĥ¡ãĥ³ãĥĪ
    -0.08
    ACHER
    -0.08
    alan
    -0.08
    ÑĪев
    -0.08
    styleType
    -0.08
    ystore
    -0.08
     ÏİÏģα
    -0.07
    ::$_
    -0.07
    unning
    -0.07
    elman
    -0.07
    POSITIVE LOGITS
     leaf
    0.06
     Maur
    0.06
    n
    0.06
    tem
    0.06
    inate
    0.06
     hy
    0.06
    ebra
    0.06
    hy
    0.06
    /single
    0.05
     drop
    0.05
    Activations Density 0.007%

    No Known Activations