© 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. 29539
    Prev
    Next
    INDEX
    Explanations

    statements related to copyright and ownership

    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
     Trick
    -0.07
     Schiff
    -0.06
    -
    -0.06
     sur
    -0.06
    mun
    -0.06
    isto
    -0.06
    ANTA
    -0.06
    anta
    -0.06
    icket
    -0.05
     trick
    -0.05
    POSITIVE LOGITS
    @qq
    0.09
    amework
    0.08
     ########.
    0.07
    PerPixel
    0.07
    hazi
    0.07
    ROTO
    0.07
    ãģĶ
    0.07
    ombine
    0.07
    FillColor
    0.07
    sez
    0.07
    Activations Density 0.002%

    No Known Activations