INDEX

Explanations

brackets and braces used in programming syntax

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

estar

-0.18

anse

-0.17

æ±

-0.16

sez

-0.15

ØµÙĩ

-0.15

tru

-0.15

¶ģ

-0.14

Ø³Ø§ÙĨÛĮ

-0.14

avian

-0.14

etter

-0.14

POSITIVE LOGITS

Lat

0.18

ixo

0.16

alara

0.15

alis

0.15

alach

0.15

0.14

ross

0.14

Lat

0.14

 Garn

0.14

 Kens

0.14

Activations Density 0.149%

brackets and braces used in programming syntax

No Comments

No Known Activations