INDEX

Explanations

references to scientific concepts and entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

.descriptor

-0.17

olor

-0.15

éŁ¿

-0.14

Ä±ma

-0.14

pil

-0.13

maal

-0.13

ritt

-0.13

 èĭ±è¯Ń

-0.13

NECTION

-0.13

Lak

-0.13

POSITIVE LOGITS

.ISupportInitialize

0.14

ÅĻÃŃz

0.14

vanced

0.14

 konkrÃ©t

0.14

centre

0.14

Ð³Ð°Ð½

0.14

ijing

0.13

osti

0.13

 Meadows

0.13

ÑĩÐ¸Ð¼

0.13

Activations Density 0.015%

references to scientific concepts and entities

No Comments

No Known Activations