INDEX

Explanations

references to mathematical or computational concepts and structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

rip

-0.16

 meaning

-0.16

-0.14

 Meaning

-0.14

yll

-0.14

meaning

-0.14

itty

-0.14

ily

-0.13

icot

-0.13

oid

-0.13

POSITIVE LOGITS

eor

0.15

IFn

0.15

edin

0.14

_collection

0.14

Ð°Ð½ÑĮ

0.14

tainment

0.14

leneck

0.14

æĺĩ

0.14

ansi

0.14

/***/

0.14

Activations Density 0.171%

references to mathematical or computational concepts and structures

No Comments

No Known Activations