INDEX

Explanations

questions related to personal experiences and advice

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

umi

-0.15

oper

-0.15

esters

-0.14

osu

-0.14

 Priority

-0.14

Orn

-0.14

olis

-0.14

 Andrews

-0.14

ahy

-0.13

gfx

-0.13

POSITIVE LOGITS

ersen

0.16

ãĥ³ãĥĦ

0.15

pdata

0.15

ÑħÐ¾Ð´

0.14

InView

0.14

(HTTP

0.14

icros

0.14

dealloc

0.14

jÃŃ

0.14

ATUS

0.14

Activations Density 0.039%

questions related to personal experiences and advice

No Comments

No Known Activations