INDEX

Explanations

numerical values and statistics within the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

eil

-0.16

SI

-0.15

NAL

-0.15

mil

-0.14

oso

-0.14

.pid

-0.14

sut

-0.14

ÃŃcio

-0.14

osi

-0.14

POSITIVE LOGITS

utch

0.14

 à¤¹à¤µ

0.13

 Schul

0.13

 Trilogy

0.13

Gra

0.13

 Vance

0.13

ë¡±

0.13

 Bookmark

0.13

GRA

0.13

-pills

0.13

Activations Density 0.037%

numerical values and statistics within the text

No Comments

No Known Activations