INDEX

Explanations

punctuations and sentence endings

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

 there

-0.17

allo

-0.16

asted

-0.15

 further

-0.14

anos

-0.14

 AyrÄ±ca

-0.14

Äįka

-0.14

idd

-0.14

 bespoke

-0.13

implicitly

-0.13

POSITIVE LOGITS

 Comb

0.19

Dub

0.19

Known

0.18

 known

0.18

 Though

0.18

 Known

0.18

 Originally

0.18

Originally

0.18

Drawing

0.17

 Unlike

0.17

Activations Density 0.436%

punctuations and sentence endings

No Comments

No Known Activations