INDEX

Explanations

code snippets and references to programming elements or functions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

oft

-0.22

oftware

-0.20

-0.15

ozor

-0.15

eur

-0.15

raph

-0.15

erd

-0.15

iciel

-0.15

oard

-0.14

AYOUT

-0.14

POSITIVE LOGITS

 Freeze

0.15

ÌĤ

0.14

unami

0.14

emonic

0.14

orges

0.14

nd

0.13

 Sullivan

0.13

quared

0.13

.fre

0.13

bootstrap

0.13

Activations Density 0.417%

code snippets and references to programming elements or functions

No Comments

No Known Activations