INDEX

Explanations

references to mutant characters or powers in a narrative context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

ejs

-0.16

affle

-0.15

Ã£n

-0.14

 Arte

-0.14

_intr

-0.14

 Maryland

-0.14

uzey

-0.14

ABB

-0.14

inkle

-0.14

ACE

-0.14

POSITIVE LOGITS

 mutant

0.34

 mutants

0.34

Mut

0.28

mut

0.27

 Magn

0.27

 Gamb

0.26

 Cable

0.26

Cyc

0.25

 Mutation

0.25

 Wolverine

0.25

Activations Density 0.014%

references to mutant characters or powers in a narrative context

No Comments

No Known Activations