INDEX

Explanations

technical specifications related to images and their formatting

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

arkin

-0.16

ullen

-0.14

reibung

-0.14

HCI

-0.14

awn

-0.14

emale

-0.13

 congress

-0.13

aiser

-0.13

 rollers

-0.13

oplast

-0.13

POSITIVE LOGITS

oley

0.17

reeNode

0.17

assel

0.16

 navigator

0.15

aland

0.15

 grav

0.14

qed

0.14

Lam

0.14

orch

0.14

 proxies

0.14

Activations Density 0.007%

technical specifications related to images and their formatting

No Comments

No Known Activations