INDEX

Explanations

references to various items, particularly documents and containers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

pector

-0.15

ĺìĿ´

-0.14

alue

-0.14

ault

-0.14

 Ð¿Ð¾Ð»ÑĮÐ·

-0.14

_SUPPORTED

-0.13

æĶ¾åľ¨

-0.13

 Hlav

-0.13

atern

-0.13

herited

-0.13

POSITIVE LOGITS

 contain

1.04

 contains

1.01

 containing

0.99

contains

0.86

 Contains

0.85

contain

0.82

Contains

0.82

 chá»©a

0.79

Containing

0.75

 ÑģÐ¾Ð´ÐµÑĢÐ¶

0.72

Activations Density 0.431%

references to various items, particularly documents and containers

No Comments

No Known Activations