INDEX

Explanations

references to totality or completeness in statements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

orum

-0.15

ekler

-0.14

 Yates

-0.14

unte

-0.13

uw

-0.13

ippo

-0.13

cher

-0.13

rous

-0.13

ieux

-0.13

POSITIVE LOGITS

 menuItem

0.15

robots

0.14

ancell

0.14

ksam

0.14

ANCELED

0.14

ANCEL

0.14

itura

0.14

ambique

0.14

UNUSED

0.14

ç©´

0.14

Activations Density 0.025%

references to totality or completeness in statements

No Comments

No Known Activations