INDEX

Explanations

references to events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

eren

-0.24

cia

-0.18

ãĤ¡

-0.17

er

-0.17

era

-0.17

ford

-0.17

adora

-0.15

ilia

-0.15

asi

-0.15

ic

-0.15

POSITIVE LOGITS

_wire

0.17

yor

0.17

owo

0.16

astered

0.15

XS

0.15

isman

0.14

CLU

0.14

anship

0.14

ufe

0.14

 ãĤŃ

0.14

Activations Density 0.028%

references to events

No Comments

No Known Activations