INDEX

Explanations

words and phrases indicating inclusion or emphasis in a context related to value or quality

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

utzer

-0.15

zano

-0.15

leep

-0.15

orm

-0.14

 zoekt

-0.14

 Erotik

-0.14

emd

-0.14

rix

-0.14

wers

-0.14

mpr

-0.14

POSITIVE LOGITS

ptr

0.15

 bÄĥng

0.14

RAW

0.14

hue

0.14

lh

0.14

ĥĿ

0.14

CompanyId

0.14

ython

0.13

Ob

0.13

Activations Density 0.002%

words and phrases indicating inclusion or emphasis in a context related to value or quality

No Comments

No Known Activations