INDEX

Explanations

mentions of various products and their characteristics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

emm

-0.20

ambi

-0.15

hea

-0.14

rug

-0.14

/licenses

-0.14

ÅĻich

-0.14

orz

-0.13

ĥĿ

-0.13

omorphic

-0.13

inis

-0.13

POSITIVE LOGITS

0.14

ubat

0.14

 themselves

0.14

0.13

 itself

0.13

arity

0.13

Ð¾Ð¶ÐµÑĤ

0.13

cub

0.13

enus

0.13

Activations Density 0.361%

mentions of various products and their characteristics

No Comments

No Known Activations