INDEX

Explanations

specific words that indicate significance or relevance in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

ales

-0.19

alars

-0.18

lamaz

-0.16

Ð½ÐµÐ½

-0.15

enet

-0.15

rams

-0.15

nen

-0.15

ixer

-0.15

recated

-0.14

YLE

-0.14

POSITIVE LOGITS

inha

0.17

vod

0.14

holm

0.14

 Ã¼zer

0.14

TTY

0.14

icao

0.14

StateManager

0.14

ĴĮ

0.14

WithDuration

0.13

IColor

0.13

Activations Density 0.016%

specific words that indicate significance or relevance in various contexts

No Comments

No Known Activations