INDEX

Explanations

mandatory actions or requirements 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 @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

ONLY

-0.15

dings

-0.14

acades

-0.14

onth

-0.14

ored

-0.14

zdy

-0.14

leich

-0.13

ÐµÑģÑĤÐ¸

-0.13

 Hayward

-0.13

ÏĩÎ¯Î±

-0.13

POSITIVE LOGITS

0.16

amet

0.14

abal

0.14

\grid

0.14

adow

0.14

ucu

0.13

be

0.13

ProcessEvent

0.13

-have

0.13

aÄŁ

0.13

Activations Density 0.033%

mandatory actions or requirements in various contexts

No Comments

No Known Activations