INDEX

Explanations

mathematical terminology related to sequences and their properties

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

anta

-0.14

(dead

-0.14

owler

-0.14

roman

-0.14

esar

-0.14

errar

-0.14

ennen

-0.14

anax

-0.14

 Neal

-0.13

 Gardner

-0.13

POSITIVE LOGITS

ÌĢ

0.16

Å¡ti

0.15

 McInt

0.15

fabric

0.15

hire

0.15

umb

0.15

chers

0.15

aders

0.15

heck

0.15

é¦

0.14

Activations Density 0.009%

mathematical terminology related to sequences and their properties

No Comments

No Known Activations