INDEX

Explanations

references to substitutions or replacements in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

uen

-0.16

éŁ¿

-0.16

ollo

-0.16

uden

-0.15

kke

-0.15

Separated

-0.15

iba

-0.15

ibel

-0.15

 Barr

-0.14

ugen

-0.14

POSITIVE LOGITS

 replaced

0.20

 replace

0.19

replace

0.19

 instead

0.18

 replacement

0.18

 substit

0.17

replacement

0.17

instead

0.17

 replacements

0.17

 yerine

0.17

Activations Density 0.215%

references to substitutions or replacements in various contexts

No Comments

No Known Activations