INDEX

Explanations

discussions related to religious themes and narratives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

arb

-0.15

appen

-0.15

ylon

-0.14

eks

-0.14

 quote

-0.14

ves

-0.14

aal

-0.13

/on

-0.13

zÄĻ

-0.13

 Pace

-0.13

POSITIVE LOGITS

@qq

0.15

 Bucc

0.15

eway

0.15

sonian

0.14

itemap

0.14

iola

0.14

mile

0.14

 ÑģÐ¾Ð±Ð¾Ð¹

0.13

æ¼«

0.13

ciz

0.13

Activations Density 0.024%

discussions related to religious themes and narratives

No Comments

No Known Activations