INDEX

Explanations

themes of punishment and imprisonment

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

ogenerated

-0.18

argon

-0.15

anco

-0.15

ocus

-0.15

 slaughtered

-0.14

äº¡

-0.14

igrants

-0.14

EDI

-0.14

 murdered

-0.14

oppel

-0.14

POSITIVE LOGITS

 sentence

0.33

 punishment

0.31

 Sentence

0.29

 sentences

0.28

 punishments

0.27

Sentence

0.26

sentence

0.25

 sentenced

0.23

 penalty

0.23

 branding

0.23

Activations Density 0.071%

themes of punishment and imprisonment

No Comments

No Known Activations