INDEX

Explanations

references to roles and responsibilities in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

fty

-0.15

alles

-0.15

wald

-0.15

week

-0.14

Å¡et

-0.14

æ¯ķ

-0.14

ensa

-0.14

iren

-0.14

ardi

-0.13

idual

-0.13

POSITIVE LOGITS

@update

0.16

 gezocht

0.16

ìĦŃ

0.15

dana

0.15

dance

0.15

Fmt

0.15

ROL

0.14

ctor

0.14

 someone

0.14

 pickle

0.14

Activations Density 0.285%

references to roles and responsibilities in various contexts

No Comments

No Known Activations