INDEX

Explanations

phrases related to significant events or medical circumstances

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

nte

-0.16

cle

-0.15

lio

-0.15

ietf

-0.14

lyph

-0.14

led

-0.14

.LookAndFeel

-0.14

alom

-0.14

 record

-0.14

éļİ

-0.14

POSITIVE LOGITS

chten

0.16

ÚĨØ§Ø±

0.15

ONTAL

0.15

 ØŃØ°

0.14

 Ð·Ð°Ð²Ð¸

0.14

imde

0.14

 eskort

0.14

ç¹Ķ

0.14

 Finn

0.14

ENTITY

0.14

Activations Density 0.017%

phrases related to significant events or medical circumstances

No Comments

No Known Activations