INDEX

Explanations

numerical values associated with dates or events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

reed

-0.16

linger

-0.16

amerate

-0.15

akens

-0.15

vell

-0.14

 Rosenstein

-0.14

lingen

-0.13

eview

-0.13

optera

-0.13

undle

-0.13

POSITIVE LOGITS

th

0.22

hs

0.15

st

0.15

't

0.14

's

0.14

Ùĭ

0.14

inf

0.13

nd

0.13

Ì

0.13

ges

0.13

Activations Density 0.019%

numerical values associated with dates or events

No Comments

No Known Activations