Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 19-LLAMASCOPE-RES-32K
    6. 25761
    Prev
    Next
    INDEX
    Explanations

    critical commentary on film quality and plot execution

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ulu
    -0.16
    itos
    -0.15
    eward
    -0.14
    iban
    -0.14
    inal
    -0.14
    иÑĤоÑĢ
    -0.14
    ift
    -0.14
     Ãĸr
    -0.14
    ÑĭÑģ
    -0.13
     regardless
    -0.13
    POSITIVE LOGITS
     indeed
    0.96
     Indeed
    0.75
    Indeed
    0.73
    inde
    0.71
     totiž
    0.57
     fact
    0.55
     actually
    0.47
    actually
    0.41
    fact
    0.36
     Actually
    0.33
    Activations Density 0.261%

    No Known Activations