INDEX

Explanations

terms related to social status or group dynamics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

CLR

-0.15

µ

-0.15

ContentLoaded

-0.15

è²¨

-0.14

_PD

-0.14

HD

-0.14

zag

-0.14

ltra

-0.14

(åľŁ

-0.14

_processor

-0.14

POSITIVE LOGITS

Ð½Ð¸ÑĨÑĮ

0.16

 McCorm

0.15

ermal

0.15

atters

0.14

 tooth

0.14

wright

0.14

ump

0.14

koc

0.14

eral

0.14

ness

0.14

Activations Density 0.008%

terms related to social status or group dynamics

No Comments

No Known Activations