INDEX

Explanations

references to circles or circular concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

aign

-0.20

.UnitTesting

-0.17

Circular

-0.17

 circular

-0.17

emachine

-0.17

 Circular

-0.16

AGEMENT

-0.16

eness

-0.16

åĪĳ

-0.15

raid

-0.15

POSITIVE LOGITS

Ð¾Ð²Ð¾ÑĢ

0.17

agh

0.16

-eyed

0.16

/group

0.16

uate

0.16

uo

0.15

 jerk

0.15

adian

0.15

 mesmo

0.15

Activations Density 0.030%

references to circles or circular concepts

No Comments

No Known Activations