INDEX

Explanations

quantifiable statistics or numerical data

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

uya

-0.15

luet

-0.14

LETE

-0.14

sec

-0.14

 ActionTypes

-0.14

undance

-0.13

ilon

-0.13

orate

-0.13

typeName

-0.13

ante

-0.13

POSITIVE LOGITS

kul

0.19

 majority

0.18

Sizer

0.16

 portion

0.15

ÐµÑĤÑĮ

0.14

 none

0.14

 Majority

0.14

Į

0.14

 everyone

0.14

none

0.14

Activations Density 0.077%

quantifiable statistics or numerical data

No Comments

No Known Activations