INDEX

Explanations

parts and sections of a document or article

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

ick

-0.16

eltas

-0.15

ical

-0.14

aye

-0.14

ftp

-0.13

acie

-0.13

kker

-0.13

fetch

-0.13

ograd

-0.13

HELL

-0.13

POSITIVE LOGITS

avors

0.17

 Load

0.15

 Campus

0.14

igans

0.14

 Clarkson

0.14

 Flake

0.14

ouch

0.14

getParam

0.13

zzo

0.13

ombat

0.13

Activations Density 0.027%

parts and sections of a document or article

No Comments

No Known Activations