INDEX

Explanations

geographical references and locations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

uria

-0.17

 Cobb

-0.16

ides

-0.16

LOCKS

-0.15

_CLOCK

-0.15

abox

-0.15

idan

-0.15

 pulses

-0.14

ermo

-0.14

 Pull

-0.14

POSITIVE LOGITS

 Camp

0.22

 Arrow

0.20

Camp

0.20

camp

0.19

ç®

0.19

 camp

0.19

 arrow

0.19

Arrow

0.19

-arrow

0.18

.arrow

0.18

Activations Density 0.027%

geographical references and locations

No Comments

No Known Activations