INDEX

Explanations

phrases indicating controversy or conflict surrounding allegations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

achuset

-0.17

marvin

-0.16

GenerationStrategy

-0.15

 GÃ¼r

-0.14

-Clause

-0.14

USIC

-0.14

erap

-0.13

olla

-0.13

amba

-0.13

 ALIGN

-0.13

POSITIVE LOGITS

dit

0.15

ijn

0.15

oret

0.14

bsite

0.14

åŃĹ

0.13

isks

0.13

odo

0.13

unga

0.13

ufe

0.13

onds

0.13

Activations Density 0.174%

phrases indicating controversy or conflict surrounding allegations

No Comments

No Known Activations