INDEX

Explanations

phrases related to representation 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

reich

-0.16

ery

-0.16

ÌĢ

-0.16

aday

-0.14

ê´

-0.14

ÄĽ

-0.13

spark

-0.13

åĢ

-0.13

alic

-0.13

POSITIVE LOGITS

 ÑģÐ¾Ð±Ð¾Ð¹

0.19

LEM

0.17

Ãºblica

0.16

atively

0.16

laz

0.15

acted

0.14

Lng

0.14

andal

0.14

orial

0.14

Represent

0.14

Activations Density 0.018%

phrases related to representation in various contexts

No Comments

No Known Activations