INDEX

Explanations

directional phrases and geographical indicators

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

urger

-0.16

awl

-0.16

 Ð½Ð°ÐºÐ¾Ð¿

-0.15

foon

-0.15

rama

-0.14

ContextHolder

-0.14

dyn

-0.14

hdr

-0.14

ìĬµ

-0.14

 semi

-0.14

POSITIVE LOGITS

 corner

0.22

ern

0.20

corner

0.19

ward

0.17

 corners

0.16

ohn

0.15

ERN

0.15

 Corner

0.15

-hand

0.15

 Virginia

0.15

Activations Density 0.020%

directional phrases and geographical indicators

No Comments

No Known Activations