INDEX

Explanations

references to political themes and discussions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

 Waters

-0.14

rint

-0.14

lez

-0.13

justice

-0.13

 Hardware

-0.13

etal

-0.13

å®¤

-0.13

 newPos

-0.13

QR

-0.13

-lite

-0.13

POSITIVE LOGITS

zones

0.15

">//

0.14

idden

0.14

istrovstvÃŃ

0.13

covered

0.13

FINITY

0.13

agan

0.13

æ§

0.13

 Avery

0.13

 zones

0.13

Activations Density 0.006%

references to political themes and discussions

No Comments

No Known Activations