INDEX

Explanations

structure and references related to project directories and files

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

ogue

-0.14

zsche

-0.14

TEGER

-0.13

ifu

-0.13

à¥įà¤¤à¤µ

-0.13

kat

-0.13

enberg

-0.13

chw

-0.13

nih

-0.13

ilver

-0.13

POSITIVE LOGITS

iza

0.16

entanyl

0.15

aken

0.15

ONTAL

0.14

 Bened

0.14

 ruce

0.14

 midd

0.14

WithMany

0.14

Resp

0.13

 outs

0.13

Activations Density 0.031%

structure and references related to project directories and files

No Comments

No Known Activations