INDEX

Explanations

emotional adjectives expressing varying degrees of difficulty, rarity, and risk

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

ummy

-0.16

oro

-0.16

-0.14

uzzi

-0.14

errick

-0.14

ungs

-0.14

eydi

-0.14

opensource

-0.13

aeda

-0.13

POSITIVE LOGITS

 thing

0.28

 enough

0.23

 Thing

0.19

 indeed

0.18

 addition

0.18

thing

0.17

 affair

0.17

way

0.17

 phenomena

0.16

 prospect

0.16

Activations Density 0.130%

emotional adjectives expressing varying degrees of difficulty, rarity, and risk

No Comments

No Known Activations