INDEX

Explanations

discussions surrounding critical analysis and philosophical topics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

lg

-0.16

ewis

-0.14

 Dust

-0.14

 beat

-0.13

askan

-0.13

 York

-0.13

sted

-0.13

langs

-0.13

ÑĪÑĤ

-0.13

ugins

-0.13

POSITIVE LOGITS

ulumi

0.15

ovÃŃ

0.15

NavController

0.15

 bordel

0.15

Ø§ÙĨÙĩ

0.14

olin

0.14

UInteger

0.14

ÑĪÐ¸Ð»Ð¸

0.14

usz

0.14

undos

0.13

Activations Density 0.073%

discussions surrounding critical analysis and philosophical topics

No Comments

No Known Activations