INDEX

Explanations

numeric values, particularly those relating to measurements or rates

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

Î½Î¹Î±

-0.17

 cent

-0.16

ivers

-0.14

å¶

-0.14

osals

-0.14

isks

-0.14

à¥įà¤°à¤¬

-0.14

Ã¡bado

-0.13

rown

-0.13

-actions

-0.13

POSITIVE LOGITS

arness

0.17

ocket

0.16

SSIP

0.16

deg

0.15

atab

0.15

irth

0.14

Ø¯Ø§Ø¯

0.14

Ð¾Ñĩ

0.14

åľ°æĸ¹

0.14

delivery

0.13

Activations Density 0.037%

numeric values, particularly those relating to measurements or rates

No Comments

No Known Activations