INDEX

Explanations

frequency and patterns of the word "the" in various contexts throughout the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

own

-0.15

 ours

-0.15

ered

-0.14

own

-0.13

(ed

-0.13

less

-0.12

ld

-0.12

ishly

-0.12

ord

-0.12

liest

-0.12

POSITIVE LOGITS

ses

0.29

 same

0.26

 following

0.21

 latter

0.20

 entire

0.19

 likes

0.18

(ir

0.18

odore

0.18

sse

0.18

osoph

0.18

Activations Density 3.631%

frequency and patterns of the word "the" in various contexts throughout the text

No Comments

No Known Activations