INDEX

Explanations

elements related to events, articles, and their coverage or reviews

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

hani

-0.16

ëĭ´

-0.14

iÃ£o

-0.14

adio

-0.14

phalt

-0.13

 Figures

-0.13

DBG

-0.13

edis

-0.13

jourd

-0.13

_DLL

-0.13

POSITIVE LOGITS

ounter

0.15

utomation

0.14

ocht

0.14

intel

0.14

ãĤ¤ãĥ³ãĥĪ

0.14

Ð°Ð±Ð»Ð¸ÑĨ

0.13

bai

0.13

ira

0.13

bk

0.13

Activations Density 0.240%

elements related to events, articles, and their coverage or reviews

No Comments

No Known Activations