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. 4281
    Prev
    Next
    INDEX
    Explanations

    references to product manuals and user instructions

    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
    upon
    -0.15
    ESP
    -0.14
    ra
    -0.14
    urn
    -0.13
    amat
    -0.13
    ur
    -0.13
    ingo
    -0.13
    -UA
    -0.13
    Ìī
    -0.12
     Essential
    -0.12
    POSITIVE LOGITS
     online
    1.00
    online
    0.88
     Online
    0.86
    -online
    0.82
    Online
    0.80
     ONLINE
    0.80
    _online
    0.75
     à¤ijनल
    0.63
    .online
    0.61
     Ø¢ÙĨÙĦاÛĮÙĨ
    0.58
    Activations Density 0.250%

    No Known Activations