INDEX

Explanations

phrases indicating the involvement of multiple parties or entities in a context

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

tsy

-0.17

Ð´ÑĢÐ¾Ð¼

-0.16

ÏĦÏģÎ¿

-0.16

èªĮ

-0.14

.SDK

-0.14

à¤Łà¤°

-0.14

 anything

-0.14

 åıĮçº¿

-0.14

Age

-0.13

å¤§ä¼ļ

-0.13

POSITIVE LOGITS

/or

0.17

acock

0.15

modo

0.15

destruct

0.14

azen

0.14

 sexes

0.14

ãģ£ãģ¡

0.14

upp

0.14

orts

0.14

à¸§à¸Ķ

0.13

Activations Density 0.055%

phrases indicating the involvement of multiple parties or entities in a context

No Comments

No Known Activations