INDEX

Explanations

references to reports and reporting in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

ermal

-0.16

far

-0.15

bourne

-0.15

imap

-0.15

aler

-0.15

borne

-0.15

more

-0.15

ider

-0.15

eral

-0.14

POSITIVE LOGITS

edly

0.24

ãĥ¥

0.17

htable

0.15

avis

0.15

à¸ªà¸Ķ

0.15

ufs

0.15

èĪĹ

0.15

getDb

0.15

iÅŁi

0.15

sdale

0.15

Activations Density 0.060%

references to reports and reporting in various contexts

No Comments

No Known Activations