INDEX

Explanations

references to numerical data or identifiers in a scientific or formal context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

alama

-0.14

 bitrate

-0.14

.Sdk

-0.14

ãĥ©ãĥĥãĤ¯

-0.14

icks

-0.14

ensch

-0.14

è¼¯

-0.14

Ä°Z

-0.13

ãĥ³ãĥĩ

-0.13

igu

-0.13

POSITIVE LOGITS

 resp

0.15

 HÃ¼s

0.15

ãĥįãĥ«

0.15

0.14

 kÅ¯

0.14

ãĥ©ãĥ³ãĥī

0.14

_ADV

0.13

PIX

0.13

Activations Density 0.046%

references to numerical data or identifiers in a scientific or formal context

No Comments

No Known Activations