INDEX

Explanations

phrases related to power dynamics and social hierarchies

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

>NN

-0.14

amba

-0.14

anto

-0.14

DataProvider

-0.14

Ð½Ð¾Ñĩ

-0.13

utzer

-0.13

è¡

-0.13

defs

-0.13

essim

-0.13

POSITIVE LOGITS

 Cory

0.15

 Corps

0.15

ettes

0.15

vetica

0.14

forge

0.14

etto

0.14

imals

0.14

anlar

0.14

annel

0.14

ette

0.14

Activations Density 1.799%

phrases related to power dynamics and social hierarchies

No Comments

No Known Activations