INDEX

Explanations

references to the concept of science across 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 @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

tra

-0.19

neo

-0.17

INGS

-0.17

neath

-0.17

ted

-0.16

lands

-0.16

rias

-0.16

ter

-0.15

isma

-0.15

acher

-0.15

POSITIVE LOGITS

-fiction

0.36

 fiction

0.34

 Fiction

0.30

/math

0.27

fiction

0.25

 fictional

0.24

/engine

0.24

/art

0.21

 fair

0.19

/Math

0.19

Activations Density 0.036%

references to the concept of science across various contexts

No Comments

No Known Activations