INDEX

Explanations

terms related to planetary science and exploration

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

éĺħè¯»æ¬¡æķ°

-0.16

lamaz

-0.15

ìĺ¥

-0.14

çľĭçľĭ

-0.14

ucks

-0.14

à¤¡à¤°

-0.14

dio

-0.13

 Durant

-0.13

æ¸¡

-0.13

inges

-0.13

POSITIVE LOGITS

 discovery

1.06

 Discovery

0.90

 discover

0.89

 discovered

0.84

 discoveries

0.84

 discovering

0.80

discover

0.80

Discovery

0.79

 Discover

0.77

 discovers

0.76

Activations Density 0.270%

terms related to planetary science and exploration

No Comments

No Known Activations