INDEX

Explanations

references to temporal events and actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

 soon

-0.16

lat

-0.14

gn

-0.14

 Hitch

-0.13

observable

-0.13

éī

-0.13

 Bias

-0.13

VERY

-0.13

 indeed

-0.13

 continued

-0.13

POSITIVE LOGITS

 originally

0.28

æľĢåĪĿ

0.24

 initially

0.22

original

0.20

 first

0.19

 original

0.19

Originally

0.19

 Originally

0.19

 last

0.18

first

0.17

Activations Density 0.099%

references to temporal events and actions

No Comments

No Known Activations