INDEX

Explanations

frequency of certain articles and determiners commonly used in descriptive contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

¼åĲĪ

-0.17

Ð¾Ð·Ð°

-0.17

OLEAN

-0.15

 vÃ½m

-0.15

iola

-0.15

zell

-0.15

atan

-0.14

 Painter

-0.14

uv

-0.14

rang

-0.14

POSITIVE LOGITS

 incom

0.16

 mainland

0.14

Ä±rÄ±

0.14

UED

0.14

tut

0.14

hy

0.13

lyn

0.13

toMatch

0.13

ant

0.13

 sympt

0.13

Activations Density 0.201%

frequency of certain articles and determiners commonly used in descriptive contexts

No Comments

No Known Activations