INDEX

Explanations

programming functions and networking-related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

Loader

-0.15

 loader

-0.15

iesz

-0.15

ajs

-0.15

anja

-0.15

Loading

-0.14

doc

-0.14

impse

-0.14

uai

-0.14

loader

-0.14

POSITIVE LOGITS

 pipe

0.20

 pipes

0.20

 Pipe

0.20

fds

0.19

ç®¡

0.18

_FILENO

0.17

pipes

0.17

pipe

0.17

Pip

0.16

 ÑĤÑĢÑĥÐ±

0.16

Activations Density 0.050%

programming functions and networking-related terms

No Comments

No Known Activations