INDEX

Explanations

conjunctions and phrases that imply addition or connection between ideas

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

umhur

-0.13

 upwards

-0.13

si

-0.13

'gc

-0.13

plies

-0.12

lac

-0.12

ÃŃte

-0.12

nal

-0.12

possibly

-0.12

ÑĤÑĢ

-0.12

POSITIVE LOGITS

 Also

0.24

 also

0.24

Also

0.23

also

0.21

Moreover

0.20

 Moreover

0.18

 hence

0.18

 same

0.18

 tambiÃ©n

0.17

 ÑĤÐ°ÐºÐ¶Ðµ

0.16

Activations Density 0.271%

conjunctions and phrases that imply addition or connection between ideas

No Comments

No Known Activations