INDEX

Explanations

symbols and punctuation marks that are part of titles or sections

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

ģ

-0.14

Ùĭ

-0.14

addy

-0.14

gi

-0.13

elda

-0.13

isl

-0.13

ÃŃs

-0.13

Gi

-0.13

↵

-0.13

Ã¨n

-0.13

POSITIVE LOGITS

inalg

0.16

oÅĻ

0.15

Eid

0.15

 ↵ ↵

0.14

ê¸Ķ

0.14

Č

0.14

jspx

0.13

 Consortium

0.13

------↵↵

0.13

 Vital

0.13

Activations Density 0.612%

symbols and punctuation marks that are part of titles or sections

No Comments

No Known Activations