© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 27-LLAMASCOPE-RES-32K
    11. 12587
    Prev
    Next
    INDEX
    Explanations

    technical terms and functions related to data processing and logging systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Marshall
    -0.18
     crack
    -0.17
     Mall
    -0.16
    _rsa
    -0.15
     Transparent
    -0.15
     radius
    -0.14
    elling
    -0.14
    alus
    -0.14
    iesel
    -0.14
    ELLOW
    -0.13
    POSITIVE LOGITS
     metric
    0.44
     metrics
    0.41
     Metric
    0.40
    metric
    0.36
    Metric
    0.36
     Metrics
    0.35
    _metric
    0.34
    (metric
    0.33
    Metrics
    0.33
    .metric
    0.32
    Activations Density 0.011%

    No Known Activations