INDEX

Explanations

words indicating proximity or closeness

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

uent

-0.17

seite

-0.17

reuse

-0.15

avis

-0.15

 sÃ¼r

-0.15

teil

-0.15

anse

-0.14

ssue

-0.14

flash

-0.14

odash

-0.14

POSITIVE LOGITS

/close

0.26

 proximity

0.20

 close

0.20

 clos

0.18

.close

0.17

 Close

0.17

/fast

0.17

-close

0.17

 enough

0.17

 CLOSE

0.16

Activations Density 0.049%

words indicating proximity or closeness

No Comments

No Known Activations

words indicating proximity or closeness

No Comments

No Known Activations