INDEX

Explanations

terms related to thermal properties and effects

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

(ord

-0.15

 tÃ¢y

-0.15

apan

-0.15

lam

-0.14

omi

-0.14

rig

-0.14

 kidney

-0.14

ec

-0.14

apg

-0.14

 Russo

-0.14

POSITIVE LOGITS

airie

0.16

shan

0.15

.Classes

0.15

ÑĢÐµÐ¹

0.15

ifold

0.15

ologie

0.15

Äįek

0.14

ilda

0.14

å²ģ

0.14

odynamic

0.13

Activations Density 0.004%

terms related to thermal properties and effects

No Comments

No Known Activations