INDEX

Explanations

ratios and comparisons in the context of training or performance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

ÐµÑĢÐ¸

-0.16

ÐµÑĢÑĸ

-0.15

 Kraj

-0.15

interop

-0.14

overe

-0.14

rys

-0.14

©

-0.14

medi

-0.14

Ã©ry

-0.14

lys

-0.14

POSITIVE LOGITS

ratio

0.18

 ratio

0.17

ÃŃd

0.16

ixe

0.15

contro

0.15

ixin

0.15

conto

0.14

ixa

0.14

entrant

0.14

upp

0.14

Activations Density 0.081%

ratios and comparisons in the context of training or performance

No Comments

No Known Activations