INDEX

Explanations

programming language constructs related to input/output functions and data processing

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

edBy

-0.17

xde

-0.15

ijkstra

-0.15

slaught

-0.14

 jung

-0.13

ahkan

-0.13

å±Ĭ

-0.13

ingers

-0.13

 Keys

-0.13

apore

-0.13

POSITIVE LOGITS

rend

0.16

rent

0.15

Alter

0.15

adin

0.14

Lifetime

0.14

 Rentals

0.14

quence

0.14

remium

0.14

uben

0.14

oleon

0.14

Activations Density 0.166%

programming language constructs related to input/output functions and data processing

No Comments

No Known Activations