INDEX

Explanations

mathematical properties related to exactness and symmetry in functions or mappings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

ension

-0.17

oppins

-0.17

ittings

-0.16

 Twig

-0.15

-0.14

ODE

-0.14

letters

-0.14

 INLINE

-0.13

floating

-0.13

POSITIVE LOGITS

chie

0.15

acity

0.15

Ã£n

0.15

ity

0.14

avo

0.14

Ì£

0.14

ness

0.14

æĲº

0.14

.dump

0.14

Hud

0.14

Activations Density 0.124%

mathematical properties related to exactness and symmetry in functions or mappings

No Comments

No Known Activations