INDEX

Explanations

programming-related terms and concepts related to data handling and manipulation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

oyal

-0.15

ixel

-0.14

endale

-0.14

lew

-0.14

missive

-0.14

ayette

-0.14

beck

-0.14

braco

-0.13

liÅ¡

-0.13

 Hakk

-0.13

POSITIVE LOGITS

NOW

0.15

LAG

0.14

ircuit

0.14

 permanent

0.13

innamon

0.13

éĽ

0.13

OC

0.13

rea

0.13

orry

0.13

Cly

0.13

Activations Density 0.248%

programming-related terms and concepts related to data handling and manipulation

No Comments

No Known Activations