INDEX

Explanations

terms related to police and their operations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

ean

-0.17

 gross

-0.15

unas

-0.14

onymous

-0.14

Ð±Ð°Ð²

-0.14

PRESSION

-0.14

unset

-0.14

 nost

-0.14

¶Į

-0.14

logy

-0.14

POSITIVE LOGITS

KeyEvent

0.15

 Ø¯Ø¹

0.15

umi

0.15

Ple

0.14

ongs

0.13

ole

0.13

artist

0.13

ãĥ¼ãĥł

0.13

eros

0.13

Activations Density 0.014%

terms related to police and their operations

No Comments

No Known Activations