INDEX

Explanations

terms related to identification or categorization of strains or types

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

umas

-0.18

pto

-0.18

çīĩ

-0.16

owell

-0.16

avin

-0.15

ncy

-0.15

acias

-0.15

icina

-0.15

ITO

-0.15

INLINE

-0.14

POSITIVE LOGITS

ifying

0.33

ifiable

0.28

ikit

0.28

ifications

0.27

ifiers

0.27

ifi

0.26

ical

0.26

ify

0.25

ifies

0.24

ified

0.24

Activations Density 0.004%

terms related to identification or categorization of strains or types

No Comments

No Known Activations