INDEX

Explanations

technical discussions related to software functionality and troubleshooting

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

sh

-0.14

à¸ģà¸£à¸£à¸¡

-0.14

 serious

-0.14

Din

-0.14

abi

-0.14

otta

-0.14

iene

-0.14

rell

-0.14

æ²

-0.13

 unless

-0.13

POSITIVE LOGITS

æŃ£å¸¸

0.16

successfully

0.16

swire

0.15

 erfolgreich

0.15

obel

0.15

HLT

0.14

azen

0.14

licit

0.14

Ð»Ð¾Ñĩ

0.14

 KdyÅ¾

0.14

Activations Density 0.044%

technical discussions related to software functionality and troubleshooting

No Comments

No Known Activations