INDEX

Explanations

phrases related to social interactions and relationships

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

hausen

-0.17

Ø´ÙĪ

-0.17

agos

-0.16

udic

-0.15

ousel

-0.15

ÙĬÙĩ

-0.15

jes

-0.15

udo

-0.14

ptom

-0.14

POSITIVE LOGITS

isphere

0.16

unb

0.16

 KÄ±z

0.16

mol

0.15

 themselves

0.14

selectors

0.14

ahl

0.14

ilo

0.14

oa

0.14

Rac

0.14

Activations Density 1.609%

phrases related to social interactions and relationships

No Comments

No Known Activations