INDEX

Explanations

elements related to mathematical definitions and proofs

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

arga

-0.19

ccione

-0.16

Ã½t

-0.15

aster

-0.15

åĵ¦

-0.15

-Bar

-0.14

ÙĨØ¯Ùĩ

-0.14

 Trade

-0.14

arda

-0.14

fty

-0.14

POSITIVE LOGITS

gren

0.15

åľ

0.15

auen

0.14

kÃ¼

0.14

ulo

0.14

azes

0.14

uffer

0.14

EMS

0.13

ouns

0.13

itra

0.13

Activations Density 0.077%

elements related to mathematical definitions and proofs

No Comments

No Known Activations