INDEX

Explanations

educational tools and resources for learning

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

sap

-0.15

iddle

-0.15

 Twin

-0.15

lichkeit

-0.14

 alcohol

-0.13

isting

-0.13

ikk

-0.13

vail

-0.13

åŃ¦

-0.13

avanaugh

-0.13

POSITIVE LOGITS

ownt

0.15

avra

0.14

 showc

0.14

è£ľ

0.14

oldur

0.14

usercontent

0.14

Verdana

0.14

andra

0.14

arat

0.13

ardon

0.13

Activations Density 0.333%

educational tools and resources for learning

No Comments

No Known Activations