INDEX

Explanations

instances related to the act of watching

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

imen

-0.17

andom

-0.15

ambre

-0.15

ensi

-0.15

/script

-0.15

yll

-0.15

imi

-0.15

eme

-0.14

Phot

-0.14

Ãªt

-0.14

POSITIVE LOGITS

 closely

0.30

/list

0.25

 unfold

0.23

 proceedings

0.22

rer

0.21

unfold

0.19

 television

0.19

 repl

0.19

 progress

0.18

 unfolding

0.17

Activations Density 0.082%

instances related to the act of watching

No Comments

No Known Activations