INDEX

Explanations

indicators of significant events or milestones

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

_CANNOT

-0.15

éĽħ

-0.15

esen

-0.14

insk

-0.14

/umd

-0.13

ienes

-0.13

Ð±Ð¾

-0.13

å±±å¸Ĥ

-0.13

ierz

-0.13

 lawy

-0.13

POSITIVE LOGITS

 previously

0.47

 Previously

0.41

 otherwise

0.40

Previously

0.40

 previous

0.38

 earlier

0.32

 Otherwise

0.32

otherwise

0.31

 OTHERWISE

0.29

Otherwise

0.29

Activations Density 0.245%

indicators of significant events or milestones

No Comments

No Known Activations