INDEX

Explanations

references to trust relationships between accounts in an online system

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

plate

-0.16

_plate

-0.16

ONO

-0.16

_Property

-0.14

igram

-0.14

_MR

-0.14

lacak

-0.14

 Jenner

-0.14

 noqa

-0.13

YLES

-0.13

POSITIVE LOGITS

 Canvas

0.34

Canvas

0.31

 course

0.28

 canvas

0.27

.canvas

0.27

canvas

0.25

anvas

0.25

 grade

0.25

 Course

0.24

 Grade

0.24

Activations Density 0.044%

references to trust relationships between accounts in an online system

No Comments

No Known Activations