INDEX

Explanations

various types and classifications of objects or concepts

oai_token-act-pair · gpt-4o-mini

New Auto-Interp

Configuration

fnlp/Llama-Scope-R1-Distill/400M-Slimpajama-400M-OpenR1-Math-220k/L15R

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Hzfinfdu/SlimPajama-3B and open-r1/OpenR1-Math-220k

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

ota

-0.07

elsen

-0.07

iser

-0.06

ÏĢÎ±

-0.06

jes

-0.06

sel

-0.06

isen

-0.06

efault

-0.06

uil

-0.06

POSITIVE LOGITS

wiÄħ

0.07

èİ

0.07

/sidebar

0.07

/octet

0.06

cae

0.06

athing

0.06

rypton

0.06

Ø±ÙĬØ¹

0.06

_equiv

0.06

Î´Î¹Î¬

0.06

Activations Density 0.022%

various types and classifications of objects or concepts

No Comments

No Known Activations