INDEX

Explanations

references to legal cases and patent law discussions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

DAQ

-0.18

Sit

-0.16

eldorf

-0.16

istrat

-0.15

abbo

-0.15

 lÆ°u

-0.15

ataka

-0.15

 Berger

-0.14

Ã¤l

-0.14

iggins

-0.14

POSITIVE LOGITS

uria

0.15

uve

0.15

 Camel

0.14

 deser

0.13

Dok

0.13

ORA

0.13

ur

0.13

 ä»¶

0.13

umen

0.13

brtc

0.13

Activations Density 0.013%

references to legal cases and patent law discussions

No Comments

No Known Activations