INDEX

Explanations

terms and phrases indicating distinctiveness or uniqueness in a variety of contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

chu

-0.18

ãĥ©ãĤ¯

-0.18

usk

-0.15

uir

-0.15

li

-0.15

wards

-0.15

ding

-0.14

back

-0.14

sel

-0.14

ISED

-0.14

POSITIVE LOGITS

ively

0.24

iveness

0.22

identifier

0.20

 blend

0.19

/original

0.19

_ptr

0.18

ities

0.18

 identifier

0.17

/dist

0.17

 identifiers

0.16

Activations Density 0.037%

terms and phrases indicating distinctiveness or uniqueness in a variety of contexts

No Comments

No Known Activations