INDEX

Explanations

references to media and databases

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

adaki

-0.17

 Manson

-0.15

ogle

-0.15

ç¥Ń

-0.14

ocommerce

-0.14

enha

-0.14

aylor

-0.14

istine

-0.13

ynam

-0.13

_MEDIUM

-0.13

POSITIVE LOGITS

ë§¥

0.14

ungi

0.14

bart

0.14

Ä±lÄ±m

0.14

ward

0.14

tg

0.13

Hir

0.13

doc

0.13

Activations Density 0.001%

references to media and databases

No Comments

No Known Activations