INDEX

Explanations

terms related to compliance and relevant requirements or standards

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

azo

-0.18

kas

-0.16

is

-0.16

ãģĭãģĳ

-0.16

æ³¡

-0.15

.Copy

-0.15

adium

-0.15

ict

-0.15

isel

-0.14

hdl

-0.14

POSITIVE LOGITS

astr

0.16

fully

0.16

¹

0.15

leck

0.15

ones

0.15

abaj

0.15

 kind

0.14

 protective

0.14

 persons

0.14

ally

0.14

Activations Density 0.051%

terms related to compliance and relevant requirements or standards

No Comments

No Known Activations