INDEX

Explanations

terms related to amplification in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

Ø®Ø§ÙĨÙĩ

-0.15

èĪ¬

-0.15

oble

-0.15

han

-0.14

exus

-0.14

à¸¸à¸Ĺà¸ĺ

-0.14

els

-0.13

lund

-0.13

iem

-0.13

fish

-0.13

POSITIVE LOGITS

0.15

iciar

0.14

orno

0.14

erge

0.14

asma

0.14

useum

0.14

 onLoad

0.14

iped

0.14

ERA

0.14

èį

0.14

Activations Density 0.019%

terms related to amplification in various contexts

No Comments

No Known Activations