Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit 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. 30-LLAMASCOPE-RES-32K
    6. 8450
    Prev
    Next
    INDEX
    Explanations

    expressions of attempts or efforts related to actions and decision-making

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ENARIO
    -0.14
    @js
    -0.14
    eki
    -0.13
    parator
    -0.13
    avit
    -0.13
    longleftrightarrow
    -0.13
    arella
    -0.13
    usto
    -0.13
    CREEN
    -0.13
    ì²Ń
    -0.13
    POSITIVE LOGITS
     try
    1.05
     tries
    0.96
    try
    0.94
     Try
    0.91
     attempt
    0.89
     trying
    0.88
     tried
    0.87
    Try
    0.87
     TRY
    0.84
     attempts
    0.83
    Activations Density 0.731%

    No Known Activations