INDEX

Explanations

references to characters and relationships within a familial or personal context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

Ã¡p

-0.15

Ã±as

-0.15

.openg

-0.15

Ã³i

-0.14

dg

-0.14

<pre

-0.14

deniz

-0.14

Jvm

-0.14

ext

-0.14

libc

-0.14

POSITIVE LOGITS

antom

0.14

0.13

 ones

0.13

TRS

0.13

typeparam

0.13

styl

0.13

 Ones

0.13

irty

0.13

(nullable

0.13

.design

0.12

Activations Density 0.057%

references to characters and relationships within a familial or personal context

No Comments

No Known Activations