INDEX

Explanations

terms and phrases related to architectural design and collaboration

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

rega

-0.16

ias

-0.16

annel

-0.16

iera

-0.14

 fault

-0.14

ripe

-0.14

erton

-0.14

ORIZONTAL

-0.14

owo

-0.14

cker

-0.14

POSITIVE LOGITS

 Inch

0.15

_editor

0.15

idlo

0.14

projects

0.14

 projects

0.14

ngine

0.14

 subdiv

0.14

 Modifier

0.13

apiro

0.13

modifier

0.13

Activations Density 0.158%

terms and phrases related to architectural design and collaboration

No Comments

No Known Activations