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. 16-LLAMASCOPE-RES-32K
    6. 8319
    Prev
    Next
    INDEX
    Explanations

    terms related to academic or theoretical concepts

    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
    _tD
    -0.15
     æĿ
    -0.15
    onis
    -0.14
    «ĺ
    -0.14
    hton
    -0.14
     intox
    -0.14
    emies
    -0.13
    ¯¼
    -0.13
    ho
    -0.13
    Fin
    -0.13
    POSITIVE LOGITS
    &quot
    0.18
    رÙĪÛĮ
    0.15
    &lt
    0.15
    uae
    0.14
    otal
    0.14
    msp
    0.14
    Nib
    0.14
    -webpack
    0.14
    MBED
    0.14
    Tumblr
    0.14
    Activations Density 0.013%

    No Known Activations