INDEX

Explanations

titles and descriptions of television programs and their genres

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

æĿŁ

-0.16

otide

-0.15

awan

-0.15

fuse

-0.15

uc

-0.15

apor

-0.14

iego

-0.14

ëĿ¼íĶ¼

-0.14

 patri

-0.14

als

-0.14

POSITIVE LOGITS

BBC

0.42

BBC

0.41

bbc

0.36

bbc

0.32

 programmes

0.25

 Programme

0.21

 programme

0.21

NPR

0.21

CBC

0.20

ÑĢÐ°Ð´Ð¸

0.20

Activations Density 0.224%

titles and descriptions of television programs and their genres

No Comments

No Known Activations