© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 11-LLAMASCOPE-RES-32K
    6. 20594
    Prev
    Next
    INDEX
    Explanations

    highlighted reviews and quotations from different publications

    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
    BuilderInterface
    -0.16
    icina
    -0.15
    esis
    -0.14
     ÙħÙĨÙĩ
    -0.14
    ---</
    -0.13
     Tribal
    -0.13
     ÑĤи
    -0.13
    atak
    -0.13
    rib
    -0.13
     Temp
    -0.13
    POSITIVE LOGITS
    usal
    0.15
    avel
    0.15
    oshi
    0.14
    eyen
    0.14
     اÙĦظ
    0.14
    ãĥŃãĥ¼
    0.13
    .hw
    0.13
     Sy
    0.13
    ì§ĢëıĦ
    0.13
    506
    0.13
    Activations Density 0.012%

    No Known Activations