INDEX

Explanations

specific locations or notable landmarks mentioned in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

Sle

-0.18

ayers

-0.17

ayer

-0.16

alim

-0.16

ixer

-0.15

 export

-0.15

itesse

-0.14

 region

-0.14

 Marty

-0.14

rou

-0.13

POSITIVE LOGITS

unal

0.17

WithTitle

0.16

anoia

0.15

CKER

0.15

ppo

0.15

åĿĽ

0.14

kea

0.14

ullo

0.14

ceae

0.14

ADATA

0.14

Activations Density 0.101%

specific locations or notable landmarks mentioned in the text

No Comments

No Known Activations