INDEX

Explanations

phrases indicating a variety or breadth of options

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

 maxim

-0.14

aires

-0.14

 Ð¿Ñĥ

-0.14

-0.13

à¥įà¤·à¤£

-0.13

fts

-0.13

oxid

-0.13

sein

-0.13

ÄĮ

-0.13

POSITIVE LOGITS

-ranging

0.17

 range

0.16

(er

0.16

-range

0.15

yo

0.15

alth

0.15

geÃ§

0.15

ãĤĥ

0.15

Activations Density 0.013%

phrases indicating a variety or breadth of options

No Comments

No Known Activations