INDEX

Explanations

negations related to product descriptions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

aggio

-0.17

ëį°ìĿ´íĬ¸

-0.15

 NavParams

-0.14

Spin

-0.14

.GPIO

-0.14

.Apis

-0.14

bjerg

-0.14

raya

-0.13

tero

-0.13

rze

-0.13

POSITIVE LOGITS

olla

0.15

Sul

0.15

Pri

0.15

 alias

0.15

Sle

0.14

ya

0.14

 Lawson

0.14

ãĥ³ãĥĹ

0.14

alf

0.14

inf

0.14

Activations Density 0.000%

negations related to product descriptions

No Comments

No Known Activations