INDEX

Explanations

references to Japanese Americans and their historical context

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

ator

-0.15

awning

-0.15

 transl

-0.14

ancel

-0.14

æ

-0.14

lod

-0.14

Bow

-0.14

uch

-0.13

eo

-0.13

amera

-0.13

POSITIVE LOGITS

-eslint

0.14

Ø¬ÛĮ

0.14

reste

0.14

éĽ¢

0.14

 ancest

0.14

 **/↵↵

0.14

picker

0.14

isode

0.14

etch

0.13

rico

0.13

Activations Density 0.490%

references to Japanese Americans and their historical context

No Comments

No Known Activations