INDEX

Explanations

references to specific individuals and their interactions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

astle

-0.15

cea

-0.15

ecided

-0.15

BuilderInterface

-0.15

ursal

-0.15

egov

-0.15

erap

-0.14

\FrameworkBundle

-0.14

avn

-0.14

roupon

-0.14

POSITIVE LOGITS

ish

0.15

 suite

0.15

beth

0.14

anne

0.14

adlo

0.14

boy

0.14

 Maver

0.14

ÎµÏĦ

0.14

 Prof

0.13

Activations Density 0.073%

references to specific individuals and their interactions

No Comments

No Known Activations