INDEX

Explanations

narratives focused on personal loss and historical violence

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

asel

-0.15

æ¤ħ

-0.15

Docs

-0.15

ÄĻp

-0.15

 Levi

-0.15

 Leban

-0.15

docs

-0.15

Disclosure

-0.14

onta

-0.14

ucus

-0.14

POSITIVE LOGITS

 narrator

0.19

 characters

0.15

 describing

0.15

CLR

0.14

 novel

0.14

mus

0.14

 describes

0.14

 description

0.14

 lives

0.14

 protagonist

0.14

Activations Density 0.292%

narratives focused on personal loss and historical violence

No Comments

No Known Activations