INDEX

Explanations

repetitive patterns or tendencies in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

oÅ¾

-0.16

ÑĢÑĸÐ´

-0.15

#End

-0.15

Batch

-0.15

illery

-0.14

amba

-0.14

cona

-0.14

borrow

-0.14

AppName

-0.14

leta

-0.14

POSITIVE LOGITS

0.19

0.15

adlo

0.14

OSH

0.14

strup

0.14

ÙĥÙĨ

0.14

ìĪľ

0.14

IDO

0.14

Tai

0.13

 SEEK

0.13

Activations Density 0.010%

repetitive patterns or tendencies in various contexts

No Comments

No Known Activations