© 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. 10-LLAMASCOPE-RES-32K
    11. 13743
    Prev
    Next
    INDEX
    Explanations

    references to specific entities or programming concepts associated with execution

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    imen
    -0.17
    olem
    -0.17
    que
    -0.16
    idis
    -0.14
    QUE
    -0.14
     rám
    -0.14
    icha
    -0.14
     lap
    -0.14
    lement
    -0.14
    äºŃ
    -0.14
    POSITIVE LOGITS
    ãģ¨ãģĵãĤį
    0.17
    481
    0.15
     |:
    0.14
    باØŃ
    0.14
    PLY
    0.14
     Fet
    0.14
    gage
    0.14
    ora
    0.14
     obs
    0.14
     Triple
    0.14
    Activations Density 0.006%

    No Known Activations