© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 24-LLAMASCOPE-RES-32K
    6. 18934
    Prev
    Next
    INDEX
    Explanations

    technical terms and mathematical concepts related to fluid dynamics and mechanical systems

    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
     axial
    -0.17
    rounded
    -0.15
    Curve
    -0.15
    emouth
    -0.15
    baugh
    -0.14
    borg
    -0.14
    tap
    -0.14
    clid
    -0.14
    egra
    -0.13
    rade
    -0.13
    POSITIVE LOGITS
     directions
    0.36
     direction
    0.34
     Directions
    0.30
     normals
    0.28
     normal
    0.28
     planes
    0.26
    direction
    0.26
    æĸ¹åIJij
    0.26
    Directions
    0.25
     plane
    0.25
    Activations Density 0.113%

    No Known Activations