INDEX

Explanations

references to organizations and their roles or achievements in specific contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

illard

-0.15

moth

-0.14

Specifier

-0.14

ãĥªãĤ«

-0.14

ãİ¡

-0.14

clado

-0.14

ÑıÐ±

-0.13

lam

-0.13

ufen

-0.13

uffers

-0.13

POSITIVE LOGITS

 Blick

0.15

aggio

0.14

 staff

0.14

ÑīÐµ

0.14

illis

0.13

Sik

0.13

erek

0.13

iffin

0.13

ĶåĽŀ

0.13

 condom

0.13

Activations Density 0.068%

references to organizations and their roles or achievements in specific contexts

No Comments

No Known Activations