INDEX

Explanations

references to file paths and directories in a system

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

zung

-0.20

outu

-0.17

/operators

-0.15

Ã¼lÃ¼

-0.15

ioned

-0.15

à¸£à¸ĵ

-0.15

vui

-0.14

boru

-0.14

ãĥ¼ãĥĸãĥ«

-0.14

xes

-0.14

POSITIVE LOGITS

oyal

0.16

arto

0.15

atomy

0.14

ring

0.14

jack

0.14

 ring

0.14

contest

0.14

isch

0.14

fram

0.13

Activations Density 0.007%

references to file paths and directories in a system

No Comments

No Known Activations