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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 18-LLAMASCOPE-RES-32K
    6. 28179
    Prev
    Next
    INDEX
    Explanations

    weather-related information, specifically temperatures and forecasts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OperationException
    -0.17
     Twilight
    -0.16
     scaleX
    -0.16
    bled
    -0.15
    йÑĤе
    -0.15
    -gnu
    -0.14
    ãĤ¤ãĥ¤
    -0.14
    ibur
    -0.14
    emain
    -0.14
    Ñıм
    -0.14
    POSITIVE LOGITS
     temperatures
    0.22
     temperature
    0.21
     Temperature
    0.19
    temperature
    0.18
     temps
    0.18
    .temperature
    0.17
    Temperature
    0.17
     temp
    0.16
     Tmax
    0.16
    elsius
    0.15
    Activations Density 0.011%

    No Known Activations