© 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. 10-LLAMASCOPE-RES-32K
    11. 20292
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate future intentions or plans

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wick
    -0.15
    craft
    -0.14
    pron
    -0.13
    raquo
    -0.13
    bed
    -0.13
    vision
    -0.13
     подÑħод
    -0.13
    PLE
    -0.12
    RAFT
    -0.12
    enne
    -0.12
    POSITIVE LOGITS
    åħĥ
    0.17
    orch
    0.14
     Baghd
    0.14
    ijing
    0.14
    ettle
    0.14
    lient
    0.14
    ishi
    0.13
     Plantae
    0.13
    egative
    0.13
     Volk
    0.13
    Activations Density 0.065%

    No Known Activations