INDEX

Explanations

instances of feedback or assessments related to behavior and interactions

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

ngo

-0.15

íħĲ

-0.15

kli

-0.14

ALI

-0.14

ICON

-0.14

bose

-0.14

.pat

-0.13

roti

-0.13

 RESP

-0.13

 respondsToSelector

-0.13

POSITIVE LOGITS

ichel

0.16

elly

0.15

rack

0.14

ogn

0.13

ÑĸÑĪ

0.13

æĸĻ

0.12

è£

0.12

semble

0.12

akis

0.12

aily

0.12

Activations Density 0.152%

instances of feedback or assessments related to behavior and interactions

No Comments

No Known Activations