INDEX

Explanations

phrases related to initiating and maintaining motion or processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

sel

-0.15

upiter

-0.15

Ð¾Ð´Ð°ÑĢ

-0.14

uli

-0.14

 quarterly

-0.14

yle

-0.14

 Found

-0.14

Ã¢ng

-0.14

cala

-0.13

 Discrim

-0.13

POSITIVE LOGITS

 chain

0.30

 Chain

0.25

chain

0.24

 chains

0.23

chains

0.22

 started

0.22

(chain

0.21

 wheels

0.20

Chain

0.20

 Chains

0.20

Activations Density 0.073%

phrases related to initiating and maintaining motion or processes

No Comments

No Known Activations