INDEX

Explanations

programming-related terms and data structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

 Austral

-0.15

ault

-0.15

.Compose

-0.14

licit

-0.14

 ...č↵

-0.14

LOTS

-0.14

 Hearing

-0.14

raya

-0.14

Î»Î¹ÎºÎ¬

-0.13

antry

-0.13

POSITIVE LOGITS

.TryParse

0.17

gies

0.15

sted

0.15

vy

0.14

avier

0.14

 Wilderness

0.13

akit

0.13

undy

0.13

col

0.13

Activations Density 0.021%

programming-related terms and data structures

No Comments

No Known Activations