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. 1-LLAMASCOPE-RES-32K
    6. 6808
    Prev
    Next
    INDEX
    Explanations

    references to ASP.NET technology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 1-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    erable
    -0.18
    eras
    -0.18
    ilee
    -0.15
    onders
    -0.15
    osy
    -0.14
    maids
    -0.14
    odÃŃ
    -0.14
    ÃŃna
    -0.14
    logradouro
    -0.14
    maid
    -0.14
    POSITIVE LOGITS
    _PCI
    0.14
    гал
    0.14
    uzz
    0.14
    ERCHANT
    0.14
    olic
    0.14
    arda
    0.13
     mathematic
    0.13
    unkt
    0.13
    agg
    0.13
    ÄįÃŃ
    0.13
    Activations Density 0.009%

    No Known Activations