INDEX

Explanations

terms related to evaluation or comparison of experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

iaux

-0.16

undi

-0.15

ÐºÐ°Ð¶

-0.14

Ĺi

-0.14

appiness

-0.14

olik

-0.14

taÅŁ

-0.13

½Ķ

-0.13

loff

-0.13

gn

-0.13

POSITIVE LOGITS

 ever

1.37

ever

1.05

-ever

1.04

 EVER

0.99

 Ever

0.95

Ever

0.90

 jamais

0.61

EVER

0.60

soever

0.44

 Everett

0.42

Activations Density 0.197%

terms related to evaluation or comparison of experiences

No Comments

No Known Activations