© 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. 30-LLAMASCOPE-RES-32K
    11. 22125
    Prev
    Next
    INDEX
    Explanations

    terms related to digital content management and legal implications of content use

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Lair
    -0.16
     Lad
    -0.14
    \Modules
    -0.14
    iless
    -0.13
     uploader
    -0.13
    LARI
    -0.13
    лаÑĢа
    -0.13
    ople
    -0.13
    oidal
    -0.13
    åĪĴ
    -0.13
    POSITIVE LOGITS
     link
    1.10
     links
    1.02
     Link
    0.97
    link
    0.95
    -link
    0.95
    Link
    0.92
    _link
    0.91
     Links
    0.87
    links
    0.85
     LINK
    0.85
    Activations Density 0.383%

    No Known Activations