INDEX

Explanations

snippets of code or programming elements in a technical context

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

zin

-0.16

Î»Î·

-0.14

oger

-0.14

 Sanctuary

-0.14

exus

-0.14

NOI

-0.14

 Habit

-0.13

interop

-0.13

Lam

-0.13

unci

-0.13

POSITIVE LOGITS

0.14

ikan

0.14

wc

0.13

.boost

0.13

suma

0.13

 Demp

0.13

elop

0.13

acion

0.13

 Buckley

0.13

achel

0.13

Activations Density 0.089%

snippets of code or programming elements in a technical context

No Comments

No Known Activations