INDEX

Explanations

dialogue and quotes related to notable statements or sentiments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

 Odds

-0.16

Uh

-0.14

andoned

-0.13

 odds

-0.13

Æ°á»£ng

-0.13

 Meaning

-0.13

odial

-0.13

oten

-0.13

irket

-0.12

AREN

-0.12

POSITIVE LOGITS

 credit

0.25

 bearing

0.23

 fair

0.23

 fingers

0.22

 Bearing

0.21

 apart

0.20

 equally

0.20

 Credit

0.20

credit

0.19

Credit

0.19

Activations Density 0.037%

dialogue and quotes related to notable statements or sentiments

No Comments

No Known Activations