INDEX

Explanations

sections of code or syntax related to function definitions and return statements

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

mu

-0.13

à¤®à¤¤

-0.13

('\

-0.13

esch

-0.13

utting

-0.13

ï

-0.13

.âĢ¢

-0.13

anza

-0.13

udi

-0.13

peare

-0.12

POSITIVE LOGITS

 /**↵

0.32

/**↵

0.29

/**

0.18

pst

0.16

/**↵↵

0.16

/**

0.15

 /**č↵

0.15

.infinity

0.15

_UNS

0.14

///

0.14

Activations Density 0.029%

sections of code or syntax related to function definitions and return statements

No Comments

No Known Activations