© 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. 6-LLAMASCOPE-RES-32K
    11. 6818
    Prev
    Next
    INDEX
    Explanations

    informal expressions and language related to surprise or shock

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gow
    -0.16
    crest
    -0.15
    iggins
    -0.14
    ssa
    -0.14
    _Render
    -0.14
    cona
    -0.14
    roots
    -0.14
    poser
    -0.14
    animate
    -0.13
    .spy
    -0.13
    POSITIVE LOGITS
    iç
    0.15
    é
    0.14
    .returnValue
    0.14
    oppel
    0.14
    enti
    0.14
     chấm
    0.13
     Sponge
    0.13
    å²³
    0.13
     Ragnar
    0.13
    enen
    0.13
    Activations Density 0.108%

    No Known Activations