INDEX

Explanations

references to locations and settings in narratives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

ãĥ©ãĥ³ãĥī

-0.15

é¡

-0.15

^K

-0.15

OutOfBoundsException

-0.15

Ð¾ÑĢÐ°Ð·

-0.14

SCI

-0.14

ArgumentException

-0.14

vide

-0.14

esi

-0.14

ance

-0.14

POSITIVE LOGITS

ynes

0.15

zik

0.14

plugin

0.14

 California

0.14

 Hotel

0.14

lover

0.14

 series

0.14

LOY

0.14

Activations Density 0.218%

references to locations and settings in narratives

No Comments

No Known Activations