INDEX

Explanations

references to awards and recognitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

 ãĤ±

-0.15

orang

-0.15

webtoken

-0.15

fang

-0.14

ãĥ¼ãĥ¬

-0.14

ToBounds

-0.14

)((((

-0.14

ÑĥÐ¼Ð°

-0.14

çĽĸ

-0.13

orr

-0.13

POSITIVE LOGITS

 honorable

0.46

Hon

0.42

Hon

0.38

 Honour

0.37

hon

0.36

 runner

0.36

 honour

0.35

 runners

0.35

 mention

0.34

 Mention

0.33

Activations Density 0.067%

references to awards and recognitions

No Comments

No Known Activations