INDEX

Explanations

abbreviations and terminology related to organizations or classifications

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

æ¸¡

-0.15

Ð¾ÑĤÑĮ

-0.15

Esk

-0.14

 Carnegie

-0.14

ed

-0.14

Ø¶

-0.14

ensa

-0.14

Gre

-0.14

atte

-0.14

">//

-0.14

POSITIVE LOGITS

boru

0.17

uncated

0.15

å§«

0.14

.TryParse

0.14

atics

0.14

arga

0.14

ç»

0.14

 (č↵

0.14

byss

0.14

Ø§Ø¨Ø©

0.13

Activations Density 0.020%

abbreviations and terminology related to organizations or classifications

No Comments

No Known Activations