INDEX

Explanations

references to circular shapes and structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

_Lean

-0.16

 ÙģÛĮ

-0.15

_Tis

-0.14

lug

-0.14

oupon

-0.14

ÑĥÐ²Ð°

-0.14

.UnitTesting

-0.14

ogo

-0.14

agger

-0.14

.lambda

-0.14

POSITIVE LOGITS

åľĪ

0.18

 circumference

0.18

-round

0.16

-loop

0.16

-around

0.16

å¥Ĺ

0.16

bum

0.15

ity

0.15

er

0.15

 radius

0.15

Activations Density 0.242%

references to circular shapes and structures

No Comments

No Known Activations

references to circular shapes and structures

No Comments

No Known Activations