INDEX

Explanations

references to political parties and geographic locations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

uder

-0.17

-0.16

 sank

-0.15

 sinks

-0.15

OOK

-0.15

andler

-0.15

rema

-0.15

-0.14

umbo

-0.14

ehr

-0.14

POSITIVE LOGITS

tering

0.19

ota

0.16

à¤°à¤£

0.15

 ÐºÐ°Ð·

0.14

Ä±rÄ±

0.14

Ã¼stÃ¼

0.14

.dds

0.14

OTA

0.14

/INFO

0.13

erral

0.13

Activations Density 0.047%

references to political parties and geographic locations

No Comments

No Known Activations