INDEX

Explanations

titles and keywords related to crime and mystery genres

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

rypton

-0.17

Writes

-0.15

panse

-0.15

åĩºçīĪ

-0.14

SHIP

-0.14

tÃŃ

-0.14

ÄĽst

-0.14

rary

-0.14

ibir

-0.14

rupa

-0.13

POSITIVE LOGITS

 starring

0.20

 directed

0.20

 movie

0.20

arring

0.19

 Part

0.17

aka

0.17

Pt

0.16

OST

0.16

 Directed

0.16

 featuring

0.16

Activations Density 0.097%

titles and keywords related to crime and mystery genres

No Comments

No Known Activations