INDEX

Explanations

phrases indicating relationships and connections

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

-0.18

uke

-0.14

org

-0.14

fro

-0.14

or

-0.14

-0.13

 wall

-0.13

Dw

-0.13

POSITIVE LOGITS

scoped

0.18

 Leban

0.17

acer

0.16

ãĥªãĥ¼ãĤº

0.15

.scalablytyped

0.15

 withd

0.15

Streams

0.15

ThreadId

0.15

uggage

0.14

']!='

0.14

Activations Density 0.667%

phrases indicating relationships and connections

No Comments

No Known Activations