INDEX

Explanations

key elements and characteristics related to context or classification

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

imple

-0.16

Ã¸y

-0.16

adoo

-0.15

-0.14

ikes

-0.14

alice

-0.14

wei

-0.13

POSITIVE LOGITS

bÃŃ

0.15

çĸ

0.15

 fondo

0.15

teri

0.14

 Pilot

0.14

Mind

0.14

 Ø¥ÙĦ

0.14

acin

0.14

 Mind

0.14

gger

0.14

Activations Density 0.014%

key elements and characteristics related to context or classification

No Comments

No Known Activations