© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 6925
    Prev
    Next
    INDEX
    Explanations

    quantitative descriptors indicating approximation or frequency

    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
    ãĥ¥
    -0.16
    /ui
    -0.16
    elif
    -0.15
    jug
    -0.15
    esan
    -0.15
    asan
    -0.15
    orem
    -0.14
    ivist
    -0.14
    ESS
    -0.14
    adora
    -0.14
    POSITIVE LOGITS
     dozen
    0.19
    ighted
    0.17
     exclusively
    0.17
     vest
    0.15
    ksam
    0.15
    że
    0.15
    lich
    0.14
    ãģªãģĮãĤī
    0.14
    ny
    0.14
     impossible
    0.14
    Activations Density 0.043%

    No Known Activations