INDEX

Explanations

terms related to specific product features and classifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

jes

-0.18

abar

-0.15

rad

-0.15

vic

-0.14

ãĤ£

-0.14

 sealed

-0.14

 Allen

-0.14

je

-0.14

Altern

-0.14

Ð±Ðµ

-0.14

POSITIVE LOGITS

 alike

0.38

 respectively

0.19

 equally

0.18

åĪĨåĪ«

0.16

ovsky

0.16

both

0.16

 separately

0.15

tvrt

0.15

owy

0.15

depending

0.15

Activations Density 0.146%

terms related to specific product features and classifications

No Comments

No Known Activations