© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 30-LLAMASCOPE-RES-32K
    11. 8539
    Prev
    Next
    INDEX
    Explanations

    text that includes various encoded or non-standard characters, possibly indicating different languages or script styles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åĩºåĵģèĢħ
    -0.25
     اÙĬÙĨ
    -0.20
    .shtml
    -0.20
     åºĶ
    -0.20
    ãģĹãģªãģĦ
    -0.19
    ÙİÙĥ
    -0.19
    é§ħå¾ĴæŃ©
    -0.18
     ÙĨÙĬ
    -0.18
     å°Ĩ
    -0.18
    ï¼ĮåĪĻ
    -0.17
    POSITIVE LOGITS
    èĪĩ
    0.17
    åıĬ
    0.17
    ä¹ĭ
    0.17
    æĵ
    0.17
    ï
    0.16
    åħ§
    0.16
    å·²
    0.16
    çļĦ
    0.16
    æļ
    0.16
    çĪ
    0.16
    Activations Density 0.007%

    No Known Activations