INDEX

Explanations

positive adjectives describing experiences and events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

-0.15

sans

-0.15

į¼

-0.14

lef

-0.14

 matters

-0.14

uci

-0.13

 Matters

-0.13

ista

-0.13

POSITIVE LOGITS

 little

0.26

 bunch

0.24

little

0.20

 addition

0.19

way

0.16

ittel

0.15

 opportunity

0.15

lil

0.15

 find

0.15

 start

0.15

Activations Density 0.094%

positive adjectives describing experiences and events

No Comments

No Known Activations