INDEX

Explanations

phrases indicating increases or rises in various trends or statistics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

ikk

-0.15

æ¼«

-0.14

 bunch

-0.14

 authorities

-0.14

ensa

-0.14

oder

-0.14

esen

-0.13

gem

-0.13

itele

-0.13

 essence

-0.13

POSITIVE LOGITS

 demand

0.19

 Demand

0.17

 demands

0.17

demand

0.17

 requests

0.17

 interesse

0.16

 Requests

0.16

[opt

0.16

Ð°Ð½Ð¸ÑĨ

0.15

ãģĿãģĨãģª

0.15

Activations Density 0.171%

phrases indicating increases or rises in various trends or statistics

No Comments

No Known Activations