© 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. 24-LLAMASCOPE-RES-32K
    11. 17911
    Prev
    Next
    INDEX
    Explanations

    references to hunting activities and their impact on conservation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eprom
    -0.14
    AZY
    -0.13
     exposures
    -0.13
    nano
    -0.13
    guide
    -0.13
    gear
    -0.13
    arend
    -0.13
    adro
    -0.12
     Bast
    -0.12
     transports
    -0.12
    POSITIVE LOGITS
     collecting
    0.60
     collects
    0.56
     gathering
    0.55
     collect
    0.53
     collected
    0.53
     Collect
    0.53
     collection
    0.51
    Collect
    0.50
     gather
    0.48
     gathered
    0.46
    Activations Density 0.466%

    No Known Activations