INDEX

Explanations

references to personal experiences and ongoing relationships

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

íĤ¹

-0.15

iani

-0.15

quez

-0.15

inally

-0.14

eparator

-0.14

Î¬Î½Ïī

-0.14

å·ŀå¸Ĥ

-0.14

Minute

-0.13

 licence

-0.13

uel

-0.13

POSITIVE LOGITS

 Klaus

0.17

 Town

0.17

 then

0.17

 resulting

0.15

kowski

0.15

 accordingly

0.15

_fwd

0.15

 charg

0.14

ayo

0.14

fig

0.14

Activations Density 0.270%

references to personal experiences and ongoing relationships

No Comments

No Known Activations