INDEX

Explanations

descriptive elements indicating movement and physical activity in a setting

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

 skiing

-0.16

ski

-0.15

 Pret

-0.15

Ski

-0.14

onen

-0.14

aki

-0.14

truncate

-0.14

oglob

-0.14

 snowy

-0.14

mex

-0.13

POSITIVE LOGITS

 rice

0.23

 local

0.23

 Gecko

0.21

 Rice

0.21

 temple

0.21

 locals

0.20

 villagers

0.20

Cyc

0.20

 coconut

0.19

rice

0.19

Activations Density 0.160%

descriptive elements indicating movement and physical activity in a setting

No Comments

No Known Activations