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. 10-LLAMASCOPE-RES-32K
    6. 11250
    Prev
    Next
    INDEX
    Explanations

    mentions of live performances and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ately
    -0.19
    ODE
    -0.17
    ä»¶
    -0.15
    ottes
    -0.15
    osal
    -0.15
    name
    -0.15
     ëĭ¤ìļ´ë°Ľê¸°
    -0.14
    baz
    -0.14
    wner
    -0.14
    so
    -0.14
    POSITIVE LOGITS
    oucher
    0.19
    erton
    0.15
    _framework
    0.15
    osterone
    0.14
    365
    0.14
     hÆ°á»Łng
    0.14
    yg
    0.14
    /live
    0.13
    룬리
    0.13
    aneous
    0.13
    Activations Density 0.022%

    No Known Activations