INDEX

Explanations

locations or names of places

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

 latter

-0.20

ãĤ©

-0.17

Ø¨Ø§Ø±

-0.15

Ø©

-0.15

ROTO

-0.14

.generated

-0.14

AKE

-0.14

feb

-0.13

verse

-0.13

.datab

-0.13

POSITIVE LOGITS

odore

0.39

adays

0.34

atre

0.30

atomy

0.26

phalt

0.24

gether

0.24

etheless

0.24

ÑįÑĤÐ¾Ð¼Ñĥ

0.23

bsites

0.22

greSQL

0.22

Activations Density 0.693%

locations or names of places

No Comments

No Known Activations