INDEX

Explanations

phrases that emphasize quantities and the relationships between them

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

istrovstvÃŃ

-0.17

 máº¡ch

-0.15

iverz

-0.15

ayet

-0.14

Winvalid

-0.14

KdyÅ¾

-0.14

.labelX

-0.13

DOMNode

-0.13

 bootloader

-0.13

ToProps

-0.13

POSITIVE LOGITS

 directly

0.21

 even

0.18

 already

0.18

chu

0.16

ison

0.16

 mere

0.16

·

0.16

mere

0.15

 familiar

0.15

insky

0.15

Activations Density 0.099%

phrases that emphasize quantities and the relationships between them

No Comments

No Known Activations