INDEX

Explanations

occurrences of the word "full" in various contexts, often related to comprehensive or complete offerings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

eff

-0.18

est

-0.17

jen

-0.17

-0.16

lenme

-0.16

ed

-0.16

laws

-0.16

jem

-0.15

Ø§ÙģØª

-0.15

ez

-0.15

POSITIVE LOGITS

/full

0.35

filled

0.26

ledged

0.25

(full

0.24

full

0.24

-full

0.24

erton

0.23

Full

0.23

 fled

0.22

 full

0.21

Activations Density 0.039%

occurrences of the word "full" in various contexts, often related to comprehensive or complete offerings

No Comments

No Known Activations