INDEX

Explanations

references to lists and updates of activities or information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

Å¡ti

-0.16

ìĺ

-0.15

veillance

-0.14

anness

-0.14

æĸŃ

-0.14

åª

-0.14

Luz

-0.13

engan

-0.13

lias

-0.13

drawable

-0.13

POSITIVE LOGITS

 full

0.55

 complete

0.50

(full

0.45

full

0.44

å®Įæķ´

0.43

 Full

0.42

 FULL

0.39

Full

0.39

complete

0.39

 detailed

0.37

Activations Density 0.097%

references to lists and updates of activities or information

No Comments

No Known Activations