© 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. 18-LLAMASCOPE-RES-32K
    11. 29073
    Prev
    Next
    INDEX
    Explanations

    keywords related to live performances and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nich
    -0.14
     Meta
    -0.13
     th
    -0.13
    âĢ
    -0.13
    ,www
    -0.13
    ideshow
    -0.12
     d
    -0.12
     Grad
    -0.12
     map
    -0.12
     meta
    -0.12
    POSITIVE LOGITS
     addCriterion
    0.15
    _fecha
    0.14
     undermin
    0.14
     ngÃły
    0.14
    agit
    0.14
     ÙħÙĤدÙħ
    0.14
    ero
    0.14
    anggal
    0.13
    нÑĥ
    0.13
    ember
    0.13
    Activations Density 0.052%

    No Known Activations