INDEX

Explanations

terms related to the concept of "presidential" or referential context associated with leadership

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

thro

-0.15

Ð°Ð·Ð°

-0.15

chin

-0.15

kinson

-0.15

tempts

-0.15

ackers

-0.14

)prepare

-0.14

ks

-0.14

ts

-0.14

estic

-0.14

POSITIVE LOGITS

 pres

0.31

 Pres

0.29

pres

0.25

.pres

0.23

Pres

0.23

-pres

0.23

umably

0.21

byter

0.20

byterian

0.19

_pres

0.19

Activations Density 0.010%

terms related to the concept of "presidential" or referential context associated with leadership

No Comments

No Known Activations