INDEX

Explanations

terms related to affirmations, beliefs, and performance metrics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

Ã¶st

-0.15

omen

-0.14

ETA

-0.14

 alike

-0.14

 Ð´ÐµÑĢ

-0.13

ind

-0.13

oe

-0.13

ostel

-0.13

_navigation

-0.13

::::::::::::::::::::::::::::::::

-0.13

POSITIVE LOGITS

zim

0.18

orial

0.15

iali

0.15

ivent

0.14

Mountain

0.14

urile

0.14

ymes

0.14

scar

0.14

anut

0.14

Activations Density 0.097%

terms related to affirmations, beliefs, and performance metrics

No Comments

No Known Activations