INDEX

Explanations

punctuations and phrases that suggest user interaction 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 @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

andas

-0.15

edn

-0.14

ridged

-0.14

?type

-0.13

obic

-0.13

ovement

-0.13

iferay

-0.13

raci

-0.13

 Daly

-0.13

 Kear

-0.13

POSITIVE LOGITS

oyo

0.15

gang

0.14

leh

0.13

lef

0.13

trail

0.13

ARA

0.13

.Cascade

0.13

mac

0.13

onde

0.13

 --->

0.13

Activations Density 0.222%

punctuations and phrases that suggest user interaction or requests for information

No Comments

No Known Activations