INDEX

Explanations

references to educational degrees and their classifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

 Degree

-0.19

degree

-0.18

gram

-0.18

tures

-0.18

deg

-0.17

dog

-0.17

Degree

-0.17

seed

-0.16

degrees

-0.16

ken

-0.16

POSITIVE LOGITS

0.31

 Celsius

0.24

-gr

0.20

eview

0.19

 holder

0.19

 holders

0.19

-long

0.18

-holder

0.18

es

0.18

eeee

0.17

Activations Density 0.020%

references to educational degrees and their classifications

No Comments

No Known Activations