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. 29-LLAMASCOPE-RES-32K
    6. 12549
    Prev
    Next
    INDEX
    Explanations

    references to public versus private funding and the impact on education

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.29.hook_resid_post
    Hook Layer
    29
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ilm
    -0.16
    UNUSED
    -0.15
    ÙĦÙħÙĩ
    -0.14
    aji
    -0.14
    osl
    -0.13
    ispecies
    -0.13
    ãĥ³ãĤ¸
    -0.13
    лÑıв
    -0.13
    illard
    -0.13
    keit
    -0.12
    POSITIVE LOGITS
     public
    1.51
    public
    1.28
     Public
    1.25
     PUBLIC
    1.18
    Public
    1.13
    -public
    1.09
    .public
    1.02
    _public
    1.00
    PUBLIC
    1.00
     pubb
    0.99
    Activations Density 0.593%

    No Known Activations