INDEX

Explanations

terms related to restoration and recovery

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

iedo

-0.18

aho

-0.17

byss

-0.16

è¿·

-0.16

ÃŃas

-0.16

sten

-0.16

bras

-0.15

utsch

-0.15

zig

-0.15

ÅĦst

-0.14

POSITIVE LOGITS

orative

0.37

orer

0.29

ful

0.28

ocking

0.27

 assured

0.27

repo

0.27

ock

0.26

rooms

0.25

oring

0.25

ored

0.25

Activations Density 0.014%

terms related to restoration and recovery

No Comments

No Known Activations