INDEX

Explanations

phrases that indicate upward movement or progress

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

 downhill

-0.32

 downwards

-0.25

 downward

-0.25

 decreasing

-0.24

 decreased

-0.23

 Down

-0.22

down

-0.22

 Decre

-0.22

Decre

-0.22

 down

-0.21

POSITIVE LOGITS

 rise

0.49

 rises

0.44

 rising

0.43

 climb

0.42

 ascent

0.42

 risen

0.42

 climbing

0.41

 Rise

0.40

 raise

0.40

-rise

0.40

Activations Density 0.221%

phrases that indicate upward movement or progress

No Comments

No Known Activations