INDEX

Explanations

technical programming terms and constructs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

igli

-0.15

CLOCKS

-0.15

oya

-0.15

rello

-0.14

vetica

-0.14

 srand

-0.14

ÏģÎ¯Î¿Ïħ

-0.14

uxe

-0.14

ifo

-0.14

isci

-0.14

POSITIVE LOGITS

mov

0.14

Ø²

0.14

vie

0.14

 ÄĳÃ¢u

0.14

ared

0.14

0.13

agle

0.13

 Unicorn

0.13

 Bills

0.13

 Abort

0.13

Activations Density 0.232%

technical programming terms and constructs

No Comments

No Known Activations