© 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. 29-LLAMASCOPE-RES-32K
    11. 17785
    Prev
    Next
    INDEX
    Explanations

    statements emphasizing the importance of factors or values in discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.29.hook_resid_post
    Hook Layer
    29
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PEAR
    -0.14
    INLINE
    -0.14
    hevik
    -0.14
    dna
    -0.14
    uale
    -0.13
    hf
    -0.13
    EFI
    -0.13
    tainment
    -0.13
    ville
    -0.13
    asan
    -0.13
    POSITIVE LOGITS
     important
    0.69
    important
    0.62
    éĩįè¦ģ
    0.57
    -important
    0.55
     Important
    0.54
     import
    0.52
     importance
    0.52
     importante
    0.50
    Important
    0.50
     importantes
    0.48
    Activations Density 0.388%

    No Known Activations