INDEX

Explanations

mentions of former political leaders and officials

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

uyo

-0.16

enting

-0.15

ÃŃr

-0.15

ascar

-0.15

endum

-0.14

ÃŃda

-0.14

VG

-0.14

ipt

-0.14

ÑĸÐ½Ð³

-0.14

ilk

-0.14

POSITIVE LOGITS

 former

0.19

 bÃ½val

0.17

/pub

0.17

 Former

0.16

 helicopt

0.16

MD

0.15

Former

0.15

 alumni

0.15

former

0.15

OOT

0.15

Activations Density 0.087%

mentions of former political leaders and officials

No Comments

No Known Activations