INDEX

Explanations

references to authors and citations within 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 @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

vette

-0.17

ewood

-0.16

iminal

-0.16

æĸ

-0.15

É

-0.14

Äģn

-0.14

ricks

-0.14

aoke

-0.14

orum

-0.14

 Rouge

-0.14

POSITIVE LOGITS

et

0.26

zb

0.14

 grown

0.13

.scalablytyped

0.13

 Nielsen

0.13

 Peters

0.13

DSP

0.13

uni

0.13

bat

0.12

Activations Density 0.171%

references to authors and citations within the text

No Comments

No Known Activations