INDEX

Explanations

programming language constructs and functions related to data manipulation

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

-0.15

ustos

-0.15

}elseif

-0.14

ÅĽÄĩ

-0.14

olas

-0.13

ulia

-0.13

 Respect

-0.13

#:

-0.13

okens

-0.13

ircle

-0.13

POSITIVE LOGITS

onders

0.15

anik

0.14

illisecond

0.14

','','

0.14

èħ

0.14

anje

0.13

hire

0.13

Ð¿Ð¾ÑĢ

0.13

unsch

0.13

Activations Density 6.331%

programming language constructs and functions related to data manipulation

No Comments

No Known Activations