INDEX

Explanations

phrases indicating a zero tolerance policy or concept

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

md

-0.15

reek

-0.15

liqu

-0.15

lov

-0.14

SSION

-0.14

oug

-0.14

uk

-0.14

ei

-0.13

rik

-0.13

.arraycopy

-0.13

POSITIVE LOGITS

/null

0.21

/no

0.18

/full

0.18

/free

0.17

ighted

0.16

MQ

0.15

çłģ

0.15

obile

0.15

idge

0.15

ToOne

0.15

Activations Density 0.029%

phrases indicating a zero tolerance policy or concept

No Comments

No Known Activations