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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 7-LLAMASCOPE-RES-32K
    6. 6243
    Prev
    Next
    INDEX
    Explanations

    language related to dynamism and adaptability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    erman
    -0.16
    .nlm
    -0.16
    icari
    -0.15
    kü
    -0.15
    iá»ĥu
    -0.15
    amer
    -0.14
    anto
    -0.14
    .assertIsNot
    -0.14
    .onDestroy
    -0.14
    ignet
    -0.14
    POSITIVE LOGITS
    ool
    0.16
    atic
    0.14
    unkt
    0.14
    åıĺåĮĸ
    0.14
    590
    0.14
    ichel
    0.14
    545
    0.14
    swers
    0.14
    uckle
    0.14
    all
    0.14
    Activations Density 0.026%

    No Known Activations