INDEX

Explanations

references to public figures or entities involved in political discussions

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

ifo

-0.16

pard

-0.16

azz

-0.15

borrow

-0.14

aw

-0.14

oom

-0.14

ue

-0.14

Äĥm

-0.14

gly

-0.13

 Crack

-0.13

POSITIVE LOGITS

andro

0.18

duto

0.15

&E

0.15

resher

0.15

olv

0.15

getSingleton

0.14

cen

0.14

XR

0.14

ornings

0.14

etro

0.14

Activations Density 0.063%

references to public figures or entities involved in political discussions

No Comments

No Known Activations