INDEX

Explanations

patterns or structures within code or programming syntax

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

iki

-0.16

inos

-0.15

 ↵  ↵

-0.15

 ↵↵

-0.14

 ↵↵↵↵

-0.14

 ↵↵↵↵↵

-0.14

ohn

-0.14

ereotype

-0.14

 ↵↵↵

-0.14

ese

-0.14

POSITIVE LOGITS

mixed

0.15

oret

0.15

zik

0.14

 Kath

0.14

 antioxid

0.14

ë²

0.13

anken

0.13

Maz

0.13

fur

0.13

Activations Density 0.155%

patterns or structures within code or programming syntax

No Comments

No Known Activations