INDEX

Explanations

expressions related to convenience and ease of access in learning or entertainment experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

yst

-0.15

un

-0.15

awan

-0.15

 Crown

-0.15

Un

-0.14

icas

-0.14

yt

-0.14

Int

-0.14

Pos

-0.14

POSITIVE LOGITS

 sitting

0.21

sit

0.18

 anywhere

0.17

 home

0.17

Anywhere

0.17

arm

0.16

èĪĴ

0.16

 convenience

0.16

sburg

0.16

 Sitting

0.16

Activations Density 0.131%

expressions related to convenience and ease of access in learning or entertainment experiences

No Comments

No Known Activations