INDEX

Explanations

references to programming constructs and structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

estro

-0.15

 Perez

-0.15

uche

-0.14

ander

-0.14

central

-0.14

 Ð¿ÑĢÐµÐ¼

-0.14

 PÃ©

-0.14

áº¢

-0.14

POSITIVE LOGITS

adal

0.14

 Crash

0.14

pson

0.14

eparator

0.14

emo

0.14

ormal

0.14

ilia

0.14

dere

0.14

onia

0.14

gress

0.14

Activations Density 0.267%

references to programming constructs and structures

No Comments

No Known Activations