© 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. 7642
    Prev
    Next
    INDEX
    Explanations

    descriptions of accommodation features and amenities

    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
    ateria
    -0.17
    iser
    -0.15
    ignon
    -0.15
    rist
    -0.15
    ibbon
    -0.15
     swimming
    -0.14
     Bedrooms
    -0.14
    urge
    -0.14
    iscard
    -0.14
    /column
    -0.14
    POSITIVE LOGITS
     twin
    0.29
     Twin
    0.27
     fut
    0.27
     queen
    0.27
     Queen
    0.25
     fold
    0.24
     Fut
    0.23
    queen
    0.22
     bunk
    0.21
    Queen
    0.20
    Activations Density 0.043%

    No Known Activations