INDEX

Explanations

references to governmental actions and public health measures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

 Oliv

-0.15

ienen

-0.14

.mybatis

-0.14

 Peek

-0.14

 tslint

-0.14

 temin

-0.14

 Transit

-0.13

 Seam

-0.13

atica

-0.13

RESOURCE

-0.13

POSITIVE LOGITS

 Government

0.21

 Hospitality

0.20

 England

0.20

 Boris

0.19

 Cobra

0.19

 hospitality

0.19

Tier

0.18

Government

0.18

 Tier

0.18

England

0.17

Activations Density 0.021%

references to governmental actions and public health measures

No Comments

No Known Activations