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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 88719
    Prev
    Next
    INDEX
    Explanations

    technical terms and conditions related to option settings or configurations

    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
    ourt
    -0.07
     fert
    -0.07
    ence
    -0.06
    anos
    -0.06
     Pink
    -0.06
    vez
    -0.06
    ivot
    -0.06
    ëĭ¨
    -0.06
    ropol
    -0.06
     Curt
    -0.06
    POSITIVE LOGITS
    çļĦè¯Ŀ
    0.09
     thì
    0.07
    oÄį
    0.07
    ï¼ĮåĪĻ
    0.07
    -UA
    0.07
    abelle
    0.07
     maka
    0.07
    á»ijc
    0.06
     alors
    0.06
    åĪĻ
    0.06
    Activations Density 0.010%

    No Known Activations