INDEX

Explanations

discussions about achieving efficiency and managing constraints

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

estre

-0.16

ardon

-0.15

rung

-0.15

adele

-0.15

otto

-0.14

hta

-0.14

 éĥ

-0.14

olle

-0.14

/mod

-0.13

Äįel

-0.13

POSITIVE LOGITS

 accomplished

0.20

 accomplish

0.17

 productivity

0.17

0.16

 maxim

0.16

 pack

0.16

oad

0.16

 maximum

0.16

per

0.16

 packed

0.15

Activations Density 0.152%

discussions about achieving efficiency and managing constraints

No Comments

No Known Activations