INDEX

Explanations

references to groups of people and their interactions or behaviors

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

obili

-0.15

stadt

-0.15

oder

-0.15

.va

-0.14

mant

-0.14

odule

-0.14

icion

-0.14

Mvc

-0.14

__/

-0.14

Civ

-0.13

POSITIVE LOGITS

0.15

tero

0.15

aked

0.15

áº¿

0.14

 Dale

0.14

è°·

0.14

ÐºÐµÑĤ

0.14

0.13

ouver

0.13

zens

0.13

Activations Density 0.102%

references to groups of people and their interactions or behaviors

No Comments

No Known Activations