INDEX

Explanations

selected names and identifiers related to notable personalities and organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

abis

-0.14

-ÑĦ

-0.13

uforia

-0.13

EGIN

-0.13

umper

-0.13

Ã¡tica

-0.13

 presentViewController

-0.13

apsed

-0.13

Ø§ÙħÙĬ

-0.13

POSITIVE LOGITS

vetica

0.14

Slo

0.14

Fav

0.13

hud

0.13

 Traverse

0.13

alley

0.13

[]{↵

0.13

Ä±lÄ±Ã§

0.13

.scalablytyped

0.13

 fellow

0.13

Activations Density 0.286%

selected names and identifiers related to notable personalities and organizations

No Comments

No Known Activations