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. 6-LLAMASCOPE-RES-32K
    6. 10475
    Prev
    Next
    INDEX
    Explanations

    references to customer engagement and interaction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oka
    -0.16
    lez
    -0.16
    lope
    -0.15
     teb
    -0.15
    esta
    -0.15
    ahoma
    -0.15
    à¥ģलन
    -0.15
    ety
    -0.15
    atorio
    -0.14
    atal
    -0.14
    POSITIVE LOGITS
    cpy
    0.18
    orz
    0.15
     von
    0.15
    ikk
    0.14
    exion
    0.14
    hots
    0.14
    spot
    0.13
    addon
    0.13
     Von
    0.13
    .Access
    0.13
    Activations Density 0.059%

    No Known Activations