INDEX

Explanations

programming class and method definitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

maal

-0.15

oder

-0.15

ioc

-0.15

çŃĨ

-0.14

pur

-0.14

icone

-0.14

æĿ¾

-0.14

itar

-0.14

iele

-0.13

POSITIVE LOGITS

ãĥ³ãĤ¿

0.15

jÃŃ

0.15

iscard

0.15

WT

0.15

DataManager

0.15

0.14

alach

0.14

 intra

0.13

AILABLE

0.13

 Stealth

0.13

Activations Density 0.013%

programming class and method definitions

No Comments

No Known Activations