INDEX

Explanations

references to "elements" and their properties or classifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

ãģ¾ãģŁ

-0.17

iglia

-0.17

Ð°Ð¶

-0.16

 behalf

-0.16

/render

-0.15

clave

-0.14

inking

-0.14

ython

-0.14

DOT

-0.14

ough

-0.14

POSITIVE LOGITS

ials

0.18

alist

0.17

 ÑĥÐ¿ÑĢÐ°Ð²Ð»ÐµÐ½Ð¸Ñı

0.16

 createElement

0.16

errupted

0.16

(Element

0.16

arity

0.15

asticsearch

0.15

.elem

0.15

Activations Density 0.088%

references to "elements" and their properties or classifications

No Comments

No Known Activations