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. 14-LLAMASCOPE-RES-32K
    6. 13645
    Prev
    Next
    INDEX
    Explanations

    citation elements or numerical references commonly found in academic or scholarly texts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bia
    -0.17
    ania
    -0.15
    大åħ¨
    -0.15
     culture
    -0.15
     Obs
    -0.15
    ÑĤим
    -0.14
     wagon
    -0.14
    AndWait
    -0.14
     Charg
    -0.14
    hya
    -0.14
    POSITIVE LOGITS
    assin
    0.15
    gettext
    0.15
    ÙĪÛĮس
    0.14
    iable
    0.14
    à¹ģà¸ģ
    0.14
    bcm
    0.14
    ILINE
    0.14
    -images
    0.14
    UNC
    0.13
    _JS
    0.13
    Activations Density 0.021%

    No Known Activations