INDEX

Explanations

numerical values and their adjacent characters or contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

Adv

-0.16

Adv

-0.15

jes

-0.15

orth

-0.15

/animations

-0.15

trim

-0.14

.ibm

-0.14

ts

-0.14

tfoot

-0.14

 Doch

-0.14

POSITIVE LOGITS

gaz

0.19

zar

0.17

à¸§à¸Ķ

0.15

 Revolutionary

0.15

leta

0.14

 Hammer

0.14

PR

0.14

 Pill

0.14

cl

0.14

imary

0.14

Activations Density 0.007%

numerical values and their adjacent characters or contexts

No Comments

No Known Activations