INDEX

Explanations

interrogative statements and phrases that indicate questioning or requests for information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

 Ð½Ð°Ñģ

-0.16

built

-0.15

arov

-0.14

PRINTF

-0.14

ji

-0.14

Gap

-0.13

 íĽĦë³´

-0.13

.spark

-0.13

 aspir

-0.13

æı¡

-0.13

POSITIVE LOGITS

odyn

0.16

afort

0.16

kest

0.16

 there

0.15

 hasn

0.15

ovit

0.15

aar

0.14

ovice

0.14

 Æ°á»Ľc

0.14

Lif

0.13

Activations Density 0.005%

interrogative statements and phrases that indicate questioning or requests for information

No Comments

No Known Activations