INDEX

Explanations

emotional expressions and descriptions of complexity in experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

uset

-0.16

mÃŃt

-0.16

uze

-0.15

 mere

-0.15

 ntohs

-0.14

usa

-0.14

_va

-0.14

ubbo

-0.13

lige

-0.13

MD

-0.13

POSITIVE LOGITS

cul

0.16

 downright

0.15

assi

0.14

olan

0.14

/or

0.14

ctp

0.14

rani

0.14

erken

0.14

 collegiate

0.14

nut

0.14

Activations Density 0.176%

emotional expressions and descriptions of complexity in experiences

No Comments

No Known Activations