INDEX

Explanations

phrases related to comparison and consistency over time

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

 Again

-0.16

Again

-0.16

 again

-0.15

imer

-0.15

again

-0.15

\<^

-0.15

agen

-0.14

oux

-0.13

/downloads

-0.13

 AGAIN

-0.13

POSITIVE LOGITS

 usual

0.27

 previous

0.23

 always

0.21

ä»¥åīį

0.21

previous

0.21

usual

0.20

always

0.20

 yesterday

0.19

.previous

0.19

 siempre

0.18

Activations Density 0.083%

phrases related to comparison and consistency over time

No Comments

No Known Activations