INDEX

Explanations

references to frontline workers and their experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

ilig

-0.17

ndl

-0.15

uluk

-0.15

jac

-0.15

alah

-0.15

ENCHMARK

-0.15

åŀ

-0.15

Gry

-0.14

Hag

-0.14

maz

-0.14

POSITIVE LOGITS

vert

0.17

uth

0.14

elle

0.14

 segment

0.14

Re

0.13

xe

0.13

 innocent

0.13

-feed

0.13

eld

0.13

_locale

0.13

Activations Density 0.122%

references to frontline workers and their experiences

No Comments

No Known Activations