INDEX

Explanations

numeric information related to statistics or measurements

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

anel

-0.17

rike

-0.16

Ã¡ty

-0.16

oo

-0.15

othy

-0.15

OLT

-0.14

in

-0.14

uter

-0.14

oth

-0.14

Ã¶l

-0.13

POSITIVE LOGITS

ê¹

0.15

arden

0.15

zed

0.15

ulumi

0.15

 createState

0.15

ìĶ

0.14

 ÙħÛĮÙĦØ§Ø¯ÛĮ

0.14

-present

0.14

 Harm

0.14

riors

0.14

Activations Density 0.034%

numeric information related to statistics or measurements

No Comments

No Known Activations