INDEX

Explanations

occurrences of the word "a" and its significance in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

leans

-0.16

ÙĨØ³

-0.15

vens

-0.14

odore

-0.14

contro

-0.14

ode

-0.14

 elusive

-0.14

lub

-0.14

eners

-0.14

 sake

-0.14

POSITIVE LOGITS

 recent

0.25

 majority

0.23

 good

0.23

lot

0.21

 curs

0.20

 person

0.19

 major

0.18

 Recent

0.18

 study

0.18

 typical

0.18

Activations Density 0.206%

occurrences of the word "a" and its significance in various contexts

No Comments

No Known Activations