INDEX

Explanations

references to movie sequels, particularly in the context of popular film franchises

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

æ¦ľ

-0.15

ãĥ³ãĥĲ

-0.15

 Leaf

-0.14

 leaf

-0.14

ANGO

-0.14

 flipped

-0.13

 base

-0.13

ividad

-0.13

Flip

-0.13

POSITIVE LOGITS

 skup

0.14

 reun

0.14

 Contin

0.14

ogl

0.14

eniz

0.14

loy

0.14

_contin

0.13

 Append

0.13

ennifer

0.13

 âĸĪ

0.13

Activations Density 0.136%

references to movie sequels, particularly in the context of popular film franchises

No Comments

No Known Activations