© 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. 16-LLAMASCOPE-RES-32K
    11. 6564
    Prev
    Next
    INDEX
    Explanations

    references to spoken phrases or direct quotations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ongyang
    -0.15
    AtA
    -0.15
     Crowley
    -0.15
    PLUS
    -0.15
     nightmare
    -0.15
    oola
    -0.14
    _BUSY
    -0.14
    plus
    -0.14
    alet
    -0.14
    roys
    -0.13
    POSITIVE LOGITS
    меÑī
    0.15
    IBILITY
    0.14
    osa
    0.14
    éłĵ
    0.14
    umi
    0.14
    ville
    0.14
     Ipsum
    0.14
    /utility
    0.14
     #+#
    0.14
    ìĬ¨
    0.14
    Activations Density 0.000%

    No Known Activations