INDEX

Explanations

phrases related to procedural or administrative documentation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

Ñĸ

-0.17

 conf

-0.15

ÑĶ

-0.15

mat

-0.15

 quint

-0.15

 class

-0.15

 ident

-0.14

 tall

-0.14

chn

-0.14

 bart

-0.14

POSITIVE LOGITS

 ÙģÙĬ

0.22

 ÙĪ

0.22

 Ùĥ

0.20

 ÙĦ

0.20

ÂłÙħ

0.20

 ÙħÙĨ

0.19

 Ø¨Ø±

0.19

 Ø¹ÙĦÙī

0.18

ØĮ

0.18

 Ø¨Ø§

0.18

Activations Density 0.021%

phrases related to procedural or administrative documentation

No Comments

No Known Activations