INDEX

Explanations

technical and mechanical terms related to engineering and design

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-looking

-0.16

 Vers

-0.15

-like

-0.15

-0.14

imas

-0.14

 Hess

-0.14

ãĥ³ãĥĩ

-0.14

ileo

-0.13

or

-0.13

 dash

-0.13

POSITIVE LOGITS

 wise

0.17

æĸ¹éĿ¢

0.17

umat

0.17

wise

0.15

-wise

0.15

ecn

0.14

 choices

0.14

-intensive

0.14

etine

0.14

arnation

0.14

Activations Density 0.314%

technical and mechanical terms related to engineering and design

No Comments

No Known Activations