INDEX

Explanations

constructs related to programmatic function calls and data handling

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

ëį°

-0.26

ãģįãģŁ

-0.21

à¸£

-0.20

ORIZONTAL

-0.18

ãģĤãģ£ãģŁ

-0.17

ãģĤãĤĬ

-0.17

ings

-0.17

ìĦľëĬĶ

-0.16

Äį

-0.15

iferay

-0.15

POSITIVE LOGITS

eenth

0.29

ed

0.22

een

0.18

	↵	↵

0.17

rist

0.17

à¸Ļ

0.17

ÙĨ

0.16

roach

0.16

ity

0.16

 addCriterion

0.16

Activations Density 0.383%

constructs related to programmatic function calls and data handling

No Comments

No Known Activations