INDEX

Explanations

references to geographical locations and regions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

 regenerate

-0.14

 Fell

-0.14

leton

-0.14

ipur

-0.14

|-

-0.14

ust

-0.14

venir

-0.13

Ð¸ÑĨ

-0.13

PU

-0.13

ona

-0.13

POSITIVE LOGITS

coni

0.19

ÙģÙĦ

0.14

 incl

0.14

jit

0.14

jÃŃt

0.14

afÃ¼r

0.14

ras

0.14

sten

0.14

QObject

0.14

 Chatt

0.14

Activations Density 0.182%

references to geographical locations and regions

No Comments

No Known Activations