INDEX

Explanations

important verbs and phrases indicating actions or requests

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

è£ķ

-0.15

tright

-0.15

roken

-0.15

ksen

-0.15

Ø¶Ø©

-0.15

avour

-0.14

kol

-0.14

sole

-0.14

Pru

-0.14

POSITIVE LOGITS

uib

0.15

 Bark

0.15

ugo

0.15

æĬ¼

0.14

isy

0.14

Ð¾Ð´Ð¾

0.14

adesh

0.14

vin

0.14

Bug

0.14

bug

0.14

Activations Density 0.000%

important verbs and phrases indicating actions or requests

No Comments

No Known Activations