INDEX

Explanations

phrases emphasizing the concept of "everything."

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

oreach

-0.15

erer

-0.15

IENT

-0.15

ATE

-0.15

Fay

-0.14

âĤ¬

-0.14

elier

-0.13

ubi

-0.13

shows

-0.13

 Chim

-0.13

POSITIVE LOGITS

 else

0.18

bam

0.16

Äįet

0.16

auer

0.15

ihn

0.14

 klid

0.14

 Else

0.14

raÅ¾

0.13

_CONF

0.13

Activations Density 0.033%

phrases emphasizing the concept of "everything."

No Comments

No Known Activations