INDEX

Explanations

phrases indicating social or communal activities and interactions

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

us

-0.19

 Stevenson

-0.16

cul

-0.15

ecies

-0.14

ects

-0.14

us

-0.14

 Higher

-0.14

pector

-0.14

ons

-0.14

POSITIVE LOGITS

unsch

0.17

bsp

0.17

Ð¾ÐºÐµ

0.16

 ourselves

0.16

ufen

0.15

echn

0.14

.opensource

0.14

Ð»Ð°Ð·

0.14

abor

0.14

itches

0.14

Activations Density 1.279%

phrases indicating social or communal activities and interactions

No Comments

No Known Activations