INDEX

Explanations

references to evaluations and assessments related to potential, competence, or impact

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

ynes

-0.15

 lookup

-0.14

ãĥ³ãĤ¯

-0.14

uchos

-0.14

ICC

-0.13

moid

-0.13

 attainment

-0.13

ipl

-0.13

\Tests

-0.13

POSITIVE LOGITS

 situation

0.23

 possibilities

0.22

olet

0.20

 possibility

0.20

æĺ¯åĲ¦

0.20

 possibilit

0.20

 progress

0.20

 pros

0.19

 appropri

0.19

 options

0.18

Activations Density 0.156%

references to evaluations and assessments related to potential, competence, or impact

No Comments

No Known Activations