INDEX

Explanations

characters and elements related to detective or mystery narratives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

ä¸įäºĨ

-0.15

 è¡ĮæĶ¿

-0.15

enburg

-0.15

_CPP

-0.14

ÑıÑĤÐ¸Ð¹

-0.14

.dds

-0.14

AdapterManager

-0.14

imat

-0.14

ãĤ¤ãĥī

-0.14

REFER

-0.13

POSITIVE LOGITS

emy

0.15

 FEMA

0.15

bern

0.14

¿

0.14

Ð¾Ð»Ð¾Ñģ

0.14

 Gund

0.14

 (“

0.13

Ä±zÄ±

0.13

Ñ

0.13

Activations Density 0.112%

characters and elements related to detective or mystery narratives

No Comments

No Known Activations