INDEX

Explanations

articles and adjectives preceding nouns or phrases that suggest quality or characteristics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

 gratuiti

-0.16

è¼

-0.16

uplic

-0.15

orget

-0.15

plx

-0.15

orgia

-0.15

Å¡t

-0.14

åį·

-0.14

orge

-0.14

èĪŀ

-0.14

POSITIVE LOGITS

ek

0.17

imes

0.16

yect

0.15

SB

0.15

al

0.15

ate

0.15

iming

0.15

 serie

0.14

irez

0.14

SEL

0.14

Activations Density 0.192%

articles and adjectives preceding nouns or phrases that suggest quality or characteristics

No Comments

No Known Activations