INDEX

Explanations

references to locations and geographical contexts within the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

ama

-0.16

.JPG

-0.15

etr

-0.14

agn

-0.14

ito

-0.14

anja

-0.13

NgModule

-0.13

æ§

-0.13

an

-0.13

 Representative

-0.13

POSITIVE LOGITS

 Rosenstein

0.18

ÃŃrk

0.16

edl

0.16

edException

0.14

zers

0.14

ugins

0.14

sÄ±

0.14

å®¶çļĦ

0.14

edBy

0.14

osg

0.14

Activations Density 0.037%

references to locations and geographical contexts within the text

No Comments

No Known Activations