© 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. 23-LLAMASCOPE-RES-32K
    11. 11991
    Prev
    Next
    INDEX
    Explanations

    technical terms related to programming and software components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ABA
    -0.15
    oe
    -0.14
    _MACRO
    -0.14
    ä½µ
    -0.14
     Ih
    -0.14
    eature
    -0.14
    _CANNOT
    -0.14
     ëħĦëıĦë³Ħ
    -0.14
    ÐļТ
    -0.14
    aylight
    -0.13
    POSITIVE LOGITS
     we
    0.20
     ourselves
    0.17
    .cd
    0.17
     kita
    0.16
     recap
    0.14
    752
    0.14
     demonstration
    0.14
    Ñĩим
    0.14
     our
    0.14
     chúng
    0.14
    Activations Density 0.093%

    No Known Activations