INDEX

Explanations

terms related to safety and hazard prevention

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

gan

-0.17

rint

-0.17

ÐĬ

-0.16

Transmission

-0.16

 xuyÃªn

-0.16

levation

-0.15

ifest

-0.15

estre

-0.15

igne

-0.15

-extension

-0.15

POSITIVE LOGITS

azer

0.17

\grid

0.17

erson

0.15

ub

0.15

á»ģn

0.14

.proc

0.14

ed

0.14

 Hoch

0.14

Zuk

0.14

 Falk

0.14

Activations Density 0.161%

terms related to safety and hazard prevention

No Comments

No Known Activations

terms related to safety and hazard prevention

No Comments

No Known Activations