INDEX

Explanations

references to specific projects or events, particularly in a dramatic or sensational context

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

de

-0.15

sn

-0.14

duk

-0.14

 left

-0.14

IX

-0.14

 round

-0.14

-0.13

br

-0.13

POSITIVE LOGITS

zych

0.16

inz

0.15

OrNil

0.15

 skoro

0.14

 Trom

0.14

Ð²Ð¸Ñĩ

0.14

intColor

0.14

bard

0.14

iless

0.14

Ð·Ð°Ð±

0.14

Activations Density 0.018%

references to specific projects or events, particularly in a dramatic or sensational context

No Comments

No Known Activations