INDEX

Explanations

references to political leaders and their actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

heim

-0.15

AGMA

-0.15

ossier

-0.15

jac

-0.15

 nanny

-0.14

:param

-0.14

urm

-0.14

åĸ

-0.13

zem

-0.13

 protest

-0.13

POSITIVE LOGITS

 himself

0.19

¶Į

0.18

 cabinet

0.17

 Cabinet

0.17

 personally

0.17

uet

0.15

uctor

0.15

ioxide

0.15

ween

0.14

 Carrier

0.14

Activations Density 0.338%

references to political leaders and their actions

No Comments

No Known Activations