INDEX

Explanations

recurring themes and distinctive stylistic elements in narratives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

pk

-0.16

ä¼į

-0.15

uki

-0.14

azu

-0.14

anches

-0.14

lis

-0.13

for

-0.13

POSITIVE LOGITS

éĤ£ç§į

0.22

 characteristic

0.20

 usual

0.19

usual

0.18

 trademark

0.17

signature

0.17

 signature

0.17

STYLE

0.17

 style

0.17

axon

0.17

Activations Density 0.177%

recurring themes and distinctive stylistic elements in narratives

No Comments

No Known Activations