INDEX

Explanations

mentions of crimes or serious offenses

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

avou

-0.17

enth

-0.15

 PREF

-0.15

.btnClose

-0.14

ÙĪØ±ÙĨ

-0.14

UME

-0.14

rei

-0.13

ahun

-0.13

gebung

-0.13

elle

-0.13

POSITIVE LOGITS

 ALSO

0.20

 simultaneously

0.20

 ademÃ¡s

0.17

 additionally

0.16

/LICENSE

0.16

 Layers

0.16

 also

0.15

 simultaneous

0.15

izer

0.15

 concurrently

0.15

Activations Density 0.229%

mentions of crimes or serious offenses

No Comments

No Known Activations