INDEX

Explanations

terms related to neural network models and architectures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

peria

-0.15

cast

-0.15

olean

-0.15

teri

-0.15

ingham

-0.14

ersistent

-0.14

 Norton

-0.14

quam

-0.14

eyin

-0.14

ntity

-0.14

POSITIVE LOGITS

algo

0.14

alten

0.14

.exc

0.14

 HÃ¼s

0.13

aya

0.13

/Documents

0.13

onas

0.13

aken

0.13

å¹

0.13

-Ta

0.13

Activations Density 0.001%

terms related to neural network models and architectures

No Comments

No Known Activations