INDEX

Explanations

references to objects or items, particularly those that are lost or misplaced

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

ifr

-0.16

ohn

-0.16

amo

-0.16

é¾

-0.16

ibi

-0.15

 asset

-0.15

cion

-0.15

 assets

-0.14

guns

-0.14

POSITIVE LOGITS

 lying

0.23

 discarded

0.22

å¼ĥ

0.22

 dropped

0.21

 litter

0.20

 DROP

0.19

 discard

0.19

 stre

0.19

 Ð»ÐµÐ¶

0.19

dro

0.19

Activations Density 0.168%

references to objects or items, particularly those that are lost or misplaced

No Comments

No Known Activations