INDEX

Explanations

references to military operations and movements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

_Invoke

-0.15

ÑĤÑĢÐ¾Ð½

-0.14

umba

-0.14

_locator

-0.14

ugas

-0.14

seau

-0.14

deen

-0.14

oice

-0.14

Dispatcher

-0.14

çŃĴ

-0.14

POSITIVE LOGITS

hart

0.16

iyah

0.16

.scalablytyped

0.15

eko

0.14

 Rank

0.14

ektor

0.14

ê²©

0.13

von

0.13

idi

0.13

eor

0.13

Activations Density 0.255%

references to military operations and movements

No Comments

No Known Activations