INDEX

Explanations

references to caregiving and nurturing actions

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

ramer

-0.18

inho

-0.17

ADE

-0.16

Clinton

-0.15

ator

-0.15

 generics

-0.15

ators

-0.14

 Burg

-0.14

astr

-0.14

ade

-0.14

POSITIVE LOGITS

 ********************************************************************************

0.16

ÙĪØ§Ø±

0.16

aju

0.15

ãĥĭãĥĥãĤ¯

0.15

éģĵè·¯

0.15

ambah

0.15

]={↵

0.15

igel

0.14

ocratic

0.14

rium

0.14

Activations Density 0.001%

references to caregiving and nurturing actions

No Comments

No Known Activations