INDEX

Explanations

terms related to Git and version control systems

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

oby

-0.15

Kir

-0.15

 imposition

-0.15

Focus

-0.14

 Skip

-0.14

plode

-0.14

edin

-0.14

aska

-0.13

ETY

-0.13

POSITIVE LOGITS

áº¥n

0.18

onso

0.16

utsch

0.16

Ã±ana

0.16

NP

0.15

raquo

0.15

ekt

0.14

ÙĨØ§ÙĨ

0.14

indow

0.14

istol

0.14

Activations Density 0.005%

terms related to Git and version control systems

No Comments

No Known Activations