INDEX

Explanations

variety of significant nouns and adjectives related to importance and value

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

rtl

-0.16

Ð½Ð¸Ð¸

-0.15

uns

-0.15

ilst

-0.14

ighton

-0.14

mons

-0.14

sel

-0.14

anean

-0.14

rix

-0.14

 Erotik

-0.14

POSITIVE LOGITS

Lem

0.15

opes

0.15

oso

0.15

vide

0.14

 Imper

0.14

zent

0.14

 bait

0.14

Stuff

0.14

 Camp

0.13

 Ecology

0.13

Activations Density 0.031%

variety of significant nouns and adjectives related to importance and value

No Comments

No Known Activations