INDEX

Explanations

terms related to information organization and sharing in digital environments

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

ãĥ©ãĥĥãĤ¯

-0.15

-wsj

-0.15

ilen

-0.14

_excerpt

-0.13

ONA

-0.13

Łèĥ½

-0.12

 Builders

-0.12

 purple

-0.12

ì´

-0.12

TOP

-0.12

POSITIVE LOGITS

-related

0.19

ples

0.17

ulfilled

0.15

ubl

0.15

âĶ´

0.14

 itself

0.14

ê°¤

0.14

-specific

0.14

utton

0.14

pedia

0.13

Activations Density 0.222%

terms related to information organization and sharing in digital environments

No Known Activations