INDEX

Explanations

numerical representations and operations involving rounding and fractions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

 iconic

-0.16

 geometric

-0.15

ĸ

-0.15

-0.14

oten

-0.14

eward

-0.14

py

-0.14

Py

-0.14

zÄħ

-0.14

Sa

-0.14

POSITIVE LOGITS

ãĥ³ãĥķ

0.16

airie

0.15

erra

0.15

åīĽ

0.15

 pornost

0.14

 FITNESS

0.14

á»ĵi

0.14

éĻ£

0.14

ÙĨÙħ

0.14

-BEGIN

0.14

Activations Density 0.050%

numerical representations and operations involving rounding and fractions

No Comments

No Known Activations