INDEX

Explanations

terms related to adventures and exploration

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

soever

-0.19

Ð¾ÑĢÐ¾

-0.18

ãĥĨãĥ«

-0.16

ities

-0.15

enstein

-0.15

è¡¡

-0.15

bie

-0.14

avior

-0.14

.scalablytyped

-0.14

ystems

-0.14

POSITIVE LOGITS

ous

0.24

ously

0.23

ary

0.18

ogue

0.18

verse

0.17

urous

0.16

odb

0.16

ÐµÑĢÐ¿

0.16

ments

0.16

arial

0.15

Activations Density 0.018%

terms related to adventures and exploration

No Comments

No Known Activations