INDEX

Explanations

references to military organizations and ranks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

illon

-0.16

IEL

-0.16

andom

-0.15

ileo

-0.15

imet

-0.15

.openConnection

-0.14

ecure

-0.14

åĭ

-0.14

 Inspector

-0.14

POSITIVE LOGITS

.flat

0.16

burst

0.15

ukan

0.14

 baja

0.14

JsonValue

0.14

elen

0.14

ç¦ıåĪ©

0.14

imary

0.14

bsub

0.14

è¿«

0.13

Activations Density 0.383%

references to military organizations and ranks

No Comments

No Known Activations