© 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. 27-LLAMASCOPE-RES-32K
    11. 2030
    Prev
    Next
    INDEX
    Explanations

    expressions of surprise or the notion of unexpected experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ambi
    -0.15
     Actual
    -0.15
    oyal
    -0.14
    cott
    -0.14
     Said
    -0.14
    pillar
    -0.14
    κολ
    -0.14
    ÙĨداÙĨ
    -0.13
    emek
    -0.13
    ocker
    -0.13
    POSITIVE LOGITS
     otherwise
    0.36
     previously
    0.34
    otherwise
    0.29
     elsewhere
    0.27
     dream
    0.26
     Previously
    0.25
     Otherwise
    0.24
     dreamed
    0.24
    Otherwise
    0.23
     Dream
    0.22
    Activations Density 0.091%

    No Known Activations