© 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. 16-LLAMASCOPE-RES-32K
    6. 6577
    Prev
    Next
    INDEX
    Explanations

    phrases related to removal or significant change

    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
    phia
    -0.17
     zel
    -0.15
    agal
    -0.15
    -format
    -0.15
    argas
    -0.14
    format
    -0.14
    ubu
    -0.14
    erve
    -0.14
     format
    -0.14
    Format
    -0.14
    POSITIVE LOGITS
    PLIED
    0.17
    ourn
    0.16
    بار
    0.14
     stocks
    0.14
    weis
    0.14
    ska
    0.14
     Crest
    0.14
     esc
    0.14
     stock
    0.13
    íķ´ë³´
    0.13
    Activations Density 0.002%

    No Known Activations