INDEX

Explanations

references to various devices and gadgets

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

Ã§o

-0.15

ÐµÐ²Ð¸

-0.15

way

-0.15

atorium

-0.15

avigator

-0.14

stone

-0.14

iane

-0.14

STONE

-0.14

ductive

-0.14

oui

-0.14

POSITIVE LOGITS

Principal

0.16

 manufactured

0.15

 Principal

0.15

LR

0.15

 concurrent

0.14

 Concurrent

0.14

 parallel

0.14

 star

0.14

principal

0.14

Missing

0.14

Activations Density 0.006%

references to various devices and gadgets

No Comments

No Known Activations