INDEX

Explanations

phrases indicating uniqueness or specificity

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

 casing

-0.15

iko

-0.14

-regexp

-0.14

iever

-0.14

Gre

-0.14

.tb

-0.14

onaut

-0.14

tober

-0.14

azo

-0.13

CASCADE

-0.13

POSITIVE LOGITS

adge

0.14

Ð°ÐºÐ¾Ð½

0.14

addons

0.14

Ã©n

0.14

TEE

0.14

rella

0.14

zeÅĦ

0.14

hall

0.13

anners

0.13

ension

0.13

Activations Density 0.045%

phrases indicating uniqueness or specificity

No Comments

No Known Activations