INDEX

Explanations

phrases relating to military responses and actions

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

ÑĤÑĢÐ¾

-0.16

iteli

-0.15

 thao

-0.14

ibil

-0.14

íĻĺ

-0.14

ucc

-0.14

-peer

-0.14

orget

-0.14

omaly

-0.14

ICO

-0.14

POSITIVE LOGITS

 response

0.40

response

0.33

 responses

0.33

 Response

0.30

 reaction

0.30

-response

0.29

.response

0.28

 RESPONSE

0.28

 Responses

0.27

/response

0.27

Activations Density 0.165%

phrases relating to military responses and actions

No Comments

No Known Activations