INDEX

Explanations

key terms related to communication and directives

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

-UA

-0.17

senal

-0.17

stre

-0.15

ioxide

-0.15

ansi

-0.15

cctor

-0.15

GuidId

-0.15

actionDate

-0.15

(~(

-0.14

*}

-0.14

POSITIVE LOGITS

ka

0.17

0.15

ma

0.15

 Boyd

0.15

æĺ

0.15

scan

0.14

 Marcus

0.14

SON

0.14

 Basic

0.14

Activations Density 0.019%

key terms related to communication and directives

No Comments

No Known Activations