INDEX

Explanations

phrases that introduce information or sources

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

uelle

-0.15

efeller

-0.14

å¿µ

-0.13

dependent

-0.13

elerik

-0.13

gage

-0.13

pile

-0.13

Ãµes

-0.13

ÃĥO

-0.13

bucks

-0.13

POSITIVE LOGITS

ed

0.20

eza

0.18

edir

0.17

ÑģÑĮ

0.17

edo

0.16

aÅ¾

0.16

eriod

0.15

eel

0.15

ÛĮ

0.15

Activations Density 0.064%

phrases that introduce information or sources

No Comments

No Known Activations