INDEX

Explanations

references to film and media related to horror

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ç°

-0.16

ç½²

-0.14

hab

-0.14

 Clayton

-0.14

èħ

-0.13

wap

-0.13

çĺ

-0.13

yte

-0.13

æ··åĲĪ

-0.13

POSITIVE LOGITS

ignal

0.20

reu

0.17

enic

0.15

legate

0.15

inha

0.15

 restores

0.15

iba

0.15

 alertController

0.14

é®

0.14

olis

0.14

Activations Density 0.033%

references to film and media related to horror

No Comments

No Known Activations