INDEX

Explanations

ellipses or fragmented sentences, indicating pauses or incomplete thoughts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

ording

-0.17

svp

-0.15

ambre

-0.14

 Wheeler

-0.14

minus

-0.14

ãĥ¼ãĥĨ

-0.14

åĵ¥

-0.14

oba

-0.14

 Chambers

-0.14

 minus

-0.13

POSITIVE LOGITS

opsy

0.16

etc

0.15

¹

0.15

aucoup

0.14

 ucwords

0.14

Î»Ïİ

0.14

ngine

0.14

chez

0.14

atr

0.14

0.13

Activations Density 0.026%

ellipses or fragmented sentences, indicating pauses or incomplete thoughts

No Comments

No Known Activations