INDEX

Explanations

inquiries about movies and films

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

 fore

-0.16

ekli

-0.16

imax

-0.15

anh

-0.14

onomies

-0.14

 Feld

-0.14

ensch

-0.14

anship

-0.14

Ã¤Ã¤

-0.14

Hoe

-0.14

POSITIVE LOGITS

ounge

0.14

ENO

0.14

ledge

0.14

ucht

0.14

_THREAD

0.14

 Barr

0.13

=wx

0.13

yn

0.13

enne

0.13

Activations Density 0.192%

inquiries about movies and films

No Comments

No Known Activations