INDEX

Explanations

historical years, particularly those associated with significant events

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

itat

-0.18

ote

-0.15

erate

-0.15

adin

-0.15

{*

-0.14

istic

-0.14

ame

-0.14

illus

-0.14

agy

-0.14

eling

-0.14

POSITIVE LOGITS

pine

0.16

weed

0.16

 ApplicationController

0.15

éĤ¦

0.15

alta

0.15

kova

0.15

asel

0.15

heim

0.14

grams

0.14

 èĩªåĬ¨çĶŁæĪĲ

0.14

Activations Density 0.010%

historical years, particularly those associated with significant events

No Comments

No Known Activations