INDEX

Explanations

references to geographical locations and population statistics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

aleb

-0.19

ãĥ¼ãĥį

-0.14

itur

-0.14

AffineTransform

-0.14

alles

-0.13

atsapp

-0.13

ãĥªãĤ«

-0.13

alen

-0.13

ptions

-0.13

>({

-0.13

POSITIVE LOGITS

 according

1.09

according

0.92

 According

0.85

According

0.80

 accordance

0.73

ccording

0.71

per

0.66

 selon

0.65

 segÃºn

0.64

æł¹æį®

0.61

Activations Density 0.566%

references to geographical locations and population statistics

No Comments

No Known Activations