INDEX

Explanations

keywords related to events, locations, and organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

ursors

-0.14

ency

-0.14

burgh

-0.14

ACES

-0.14

ewear

-0.14

ench

-0.14

ãĥĭãĥ¡

-0.14

ego

-0.14

 Curve

-0.14

POSITIVE LOGITS

Advance

0.18

 advance

0.17

 Advance

0.17

advance

0.17

 entry

0.16

 advanced

0.16

_advance

0.15

 advancement

0.14

 Advanced

0.14

advanced

0.14

Activations Density 0.028%

keywords related to events, locations, and organizations

No Comments

No Known Activations