© 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. 11-LLAMASCOPE-RES-32K
    11. 17971
    Prev
    Next
    INDEX
    Explanations

    specific numerical guidelines and recommendations regarding homework duration for students

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Fmt
    -0.15
    icket
    -0.15
    -|
    -0.15
     Geek
    -0.14
    deaux
    -0.13
    ãĥĥãĥī
    -0.13
    nom
    -0.13
    bil
    -0.13
    unar
    -0.13
    plusplus
    -0.13
    POSITIVE LOGITS
    ÑģÑĭлки
    0.14
    หม
    0.14
    bsite
    0.14
    .dep
    0.14
    .rule
    0.14
    祥
    0.14
    .bukkit
    0.13
     dere
    0.13
    ertas
    0.13
    addock
    0.13
    Activations Density 0.281%

    No Known Activations