INDEX

Explanations

references to specific public figures and political context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

abbit

-0.18

 Alonso

-0.17

 Alan

-0.17

-al

-0.17

alg

-0.17

alm

-0.17

 Alabama

-0.17

abb

-0.16

aal

-0.16

 Alban

-0.16

POSITIVE LOGITS

cheid

0.15

0.14

.Bad

0.14

Ch

0.14

auss

0.14

BCH

0.14

 !***

0.14

áºŃu

0.14

 Ðĳ

0.14

ÂłB

0.14

Activations Density 0.061%

references to specific public figures and political context

No Comments

No Known Activations