INDEX

Explanations

phrases that imply visibility or recognition of certain qualities or characteristics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

 bá»ķ

-0.14

ifu

-0.14

aub

-0.14

ëŀĢ

-0.13

 ÑĩÑĤÐ¾Ð±Ñĭ

-0.13

tr

-0.13

kers

-0.13

_DUMP

-0.13

âĶģ

-0.12

ellan

-0.12

POSITIVE LOGITS

 throughout

0.24

 everywhere

0.23

 through

0.21

 nowhere

0.20

 whenever

0.19

sthrough

0.18

 when

0.18

 wherever

0.17

through

0.17

_through

0.16

Activations Density 0.149%

phrases that imply visibility or recognition of certain qualities or characteristics

No Comments

No Known Activations