© 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. 7597
    Prev
    Next
    INDEX
    Explanations

    mentions and references to YouTube

    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
    hu
    -0.18
     Tweets
    -0.17
     Tweet
    -0.17
    994
    -0.16
    lov
    -0.16
    roads
    -0.15
    roc
    -0.15
    .inputs
    -0.15
    way
    -0.15
    nya
    -0.15
    POSITIVE LOGITS
    tube
    0.22
     channel
    0.22
     sensation
    0.20
     tube
    0.20
     sensations
    0.19
    -channel
    0.18
     channels
    0.18
    channel
    0.17
    outu
    0.17
     Tube
    0.17
    Activations Density 0.007%

    No Known Activations