© 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. 30-LLAMASCOPE-RES-32K
    6. 17281
    Prev
    Next
    INDEX
    Explanations

    programming concepts and terms related to data structures and types

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     plur
    -0.15
     Pent
    -0.15
     ÑģÑĦ
    -0.14
    TestClass
    -0.14
    å£
    -0.13
     Beard
    -0.13
    enko
    -0.13
     inventory
    -0.13
     Mare
    -0.13
    -gap
    -0.13
    POSITIVE LOGITS
     paddle
    0.22
     TV
    0.20
     Attr
    0.19
    fusion
    0.18
    tir
    0.17
    _dy
    0.17
     Op
    0.17
     fuse
    0.17
    Attrs
    0.16
    Attr
    0.16
    Activations Density 0.001%

    No Known Activations