INDEX

Explanations

references to individuals involved in legal or public controversies

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

ennen

-0.17

 Leak

-0.16

hti

-0.16

UTIL

-0.15

ocrine

-0.15

ISC

-0.14

quet

-0.14

 Halk

-0.14

Øµ

-0.14

»¿

-0.14

POSITIVE LOGITS

ãĤ¡

0.26

unami

0.22

ãĤ§

0.21

ãĤ©

0.18

uts

0.18

gerald

0.18

ubishi

0.16

uki

0.16

 blink

0.16

ifth

0.15

Activations Density 0.047%

references to individuals involved in legal or public controversies

No Comments

No Known Activations