INDEX

Explanations

names of authors or researchers

oai_token-act-pair · gpt-4o-mini

New Auto-Interp

Configuration

fnlp/Llama-Scope-R1-Distill/800M-Slimpajama-0-OpenR1-Math-220k/L15R

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Hzfinfdu/SlimPajama-3B

Features

32,768

Data Type

float32

Hook Name

blocks.15.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

er

-0.22

rig

-0.18

set

-0.17

ress

-0.15

ns

-0.15

 æŃ

-0.15

rank

-0.14

adm

-0.14

tid

-0.14

tridge

-0.14

POSITIVE LOGITS

heim

0.16

heimer

0.15

edom

0.15

esian

0.14

kie

0.14

edTextBox

0.14

tual

0.14

amework

0.14

 Hats

0.14

 èĩªåĬ¨çĶŁæĪĲ

0.14

Activations Density 0.061%

names of authors or researchers

No Comments

No Known Activations