© 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. 25-LLAMASCOPE-RES-32K
    11. 18214
    Prev
    Next
    INDEX
    Explanations

    functions and methods related to activity lifecycle management in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    keeper
    -0.15
    ichen
    -0.15
     Keeper
    -0.15
    orta
    -0.14
    vla
    -0.14
    .library
    -0.14
    _STATIC
    -0.14
    еÑĢп
    -0.14
    erator
    -0.14
    erta
    -0.14
    POSITIVE LOGITS
     override
    0.27
    override
    0.26
     overridden
    0.25
    	override
    0.24
     Override
    0.23
     protected
    0.22
     overriding
    0.22
    protected
    0.21
     Overrides
    0.21
    overrides
    0.21
    Activations Density 0.115%

    No Known Activations