© 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. 8-LLAMASCOPE-RES-32K
    11. 8031
    Prev
    Next
    INDEX
    Explanations

    references to outdoor activities and hiking trails

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 8-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    epar
    -0.15
     doc
    -0.15
    é¡
    -0.14
     tow
    -0.14
    oked
    -0.14
    Jer
    -0.14
     like
    -0.14
     ske
    -0.14
    759
    -0.13
    iro
    -0.13
    POSITIVE LOGITS
     dét
    0.15
    peq
    0.14
    .experimental
    0.14
    _lite
    0.14
    ÑĢиз
    0.13
    /Gate
    0.13
    riad
    0.13
     Timothy
    0.13
    ima
    0.13
    ãģĭãģĹ
    0.13
    Activations Density 0.023%

    No Known Activations