INDEX

Explanations

concepts and details about time-related conditions and consequences

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

.RemoveAll

-0.17

rh

-0.16

Ãºa

-0.15

alloc

-0.14

 ÎľÎ·

-0.14

.getSelection

-0.14

UTILITY

-0.13

 saber

-0.13

 bron

-0.13

İ·

-0.13

POSITIVE LOGITS

 anymore

0.29

nor

0.28

Nor

0.23

Nor

0.23

nor

0.22

 unless

0.20

0.17

unless

0.16

ani

0.16

NOR

0.15

Activations Density 0.415%

concepts and details about time-related conditions and consequences

No Comments

No Known Activations