INDEX

Explanations

programming-related syntax and structure

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

Ð°Ð½ÑĤÐ¸

-0.16

abo

-0.15

ecer

-0.14

íĶĪ

-0.14

irit

-0.14

embedded

-0.14

logan

-0.14

ersiz

-0.14

seite

-0.13

rtl

-0.13

POSITIVE LOGITS

iams

0.17

Ware

0.14

exion

0.14

.assignment

0.14

 ÙĨØ³

0.14

_lazy

0.14

igm

0.13

Ã´ng

0.13

idan

0.13

jav

0.13

Activations Density 0.013%

programming-related syntax and structure

No Comments

No Known Activations