INDEX

Explanations

numerical identifiers or classification indicators

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

imit

-0.16

ropp

-0.15

brero

-0.15

locker

-0.14

dera

-0.14

dere

-0.14

Äįit

-0.14

IMIT

-0.13

POSITIVE LOGITS

reme

0.16

loven

0.16

Î´Î®

0.14

 éĹ

0.14

à¤ĸ

0.14

UPS

0.14

izr

0.14

odox

0.14

TAB

0.14

skins

0.13

Activations Density 0.021%

numerical identifiers or classification indicators

No Comments

No Known Activations