INDEX

Explanations

programming-related elements and structures in the text

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

OpenHelper

-0.15

isu

-0.14

krom

-0.13

antal

-0.13

auc

-0.13

_^(

-0.13

Ã£n

-0.13

chodu

-0.13

PARATOR

-0.13

istrovstvÃŃ

-0.13

POSITIVE LOGITS

 darauf

0.16

ayah

0.14

 dispers

0.13

oven

0.13

letcher

0.13

irth

0.13

ober

0.12

/mod

0.12

 =============================================================================↵

0.12

ILLS

0.12

Activations Density 29.618%

programming-related elements and structures in the text

No Comments

No Known Activations