INDEX

Explanations

references to annual events and their ordinal indicators

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

-urlencoded

-0.16

otti

-0.15

 Twice

-0.14

inish

-0.14

 ÄĮR

-0.14

-0.13

sep

-0.13

 odpad

-0.13

 serm

-0.13

FINITE

-0.13

POSITIVE LOGITS

refixer

0.15

OfClass

0.15

oder

0.15

ãĥ¬ãĥ¼

0.15

aign

0.15

aho

0.14

ink

0.14

HashCode

0.14

vine

0.14

-to

0.14

Activations Density 0.061%

references to annual events and their ordinal indicators

No Comments

No Known Activations