INDEX

Explanations

references to structures or systems that provide guidance or support 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 @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

lsen

-0.17

oday

-0.17

ongyang

-0.15

LLU

-0.15

kÃ¼

-0.15

anou

-0.15

ÛĮÚ©ÛĮ

-0.14

outu

-0.14

jÃŃÅ¾

-0.14

entials

-0.14

POSITIVE LOGITS

0.18

.Framework

0.16

hin

0.15

inkel

0.15

pan

0.14

edly

0.14

 vitae

0.14

 ausp

0.14

atic

0.14

buffers

0.14

Activations Density 0.020%

references to structures or systems that provide guidance or support in various contexts

No Comments

No Known Activations