INDEX

Explanations

mentions of the word "science" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

INGS

-0.18

Ð³Ð°

-0.17

malink

-0.17

rone

-0.16

udy

-0.16

Ð±Ð¾ÑĢ

-0.15

 Sciences

-0.15

ÑĮÑİÑĤ

-0.15

undry

-0.15

ivr

-0.15

POSITIVE LOGITS

 fiction

0.33

-fiction

0.30

 Fiction

0.28

fiction

0.23

 fictional

0.20

 fair

0.19

/math

0.18

 Fair

0.17

 fict

0.17

-policy

0.17

Activations Density 0.021%

mentions of the word "science" in various contexts

No Comments

No Known Activations