INDEX

Explanations

affirmations or expressions of certainty

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

ERS

-0.20

ÐµÑģÑĤÐ²

-0.16

oggler

-0.16

rene

-0.16

sWith

-0.16

asters

-0.16

itters

-0.16

robe

-0.15

adia

-0.15

orp

-0.15

POSITIVE LOGITS

fire

0.39

-fire

0.36

ty

0.34

foot

0.32

-foot

0.31

nder

0.29

ties

0.25

 thing

0.24

 glad

0.24

-shot

0.24

Activations Density 0.037%

affirmations or expressions of certainty

No Comments

No Known Activations