INDEX

Explanations

words and phrases associated with documentation and programming structure

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

edor

-0.17

linger

-0.16

fuse

-0.16

-prepend

-0.16

Äĥng

-0.15

ossier

-0.15

ules

-0.15

ä¾

-0.15

imiter

-0.15

elerik

-0.15

POSITIVE LOGITS

 Dick

0.18

Dick

0.16

Loc

0.15

loc

0.15

aches

0.15

etrain

0.14

 stan

0.14

arl

0.14

 Arch

0.14

Activations Density 0.023%

words and phrases associated with documentation and programming structure

No Comments

No Known Activations

words and phrases associated with documentation and programming structure

No Comments

No Known Activations