INDEX

Explanations

adjectives and qualifiers that describe qualities and characteristics

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

izen

-0.16

igon

-0.15

ending

-0.15

eson

-0.15

lush

-0.14

ather

-0.14

exo

-0.13

vel

-0.13

 Shields

-0.13

Toy

-0.13

POSITIVE LOGITS

 enough

0.23

ly

0.18

 Geile

0.18

ness

0.18

impse

0.16

 Enough

0.15

ities

0.14

nul

0.14

âĢĮØªØ±

0.14

steen

0.14

Activations Density 0.595%

adjectives and qualifiers that describe qualities and characteristics

No Comments

No Known Activations