INDEX

Explanations

numeric values and identifiers related to measurements or performance metrics

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

mÃŃt

-0.14

overy

-0.14

sterol

-0.14

à¥įà¤ªà¤°

-0.14

idea

-0.13

allet

-0.13

raz

-0.13

Ã¤h

-0.13

scanner

-0.13

iaz

-0.13

POSITIVE LOGITS

éĳĳ

0.14

ak

0.14

ë¶Ī

0.14

 boto

0.14

.simps

0.13

 Allocate

0.13

awn

0.13

åįļ

0.13

 otherwise

0.13

 Jamal

0.13

Activations Density 0.199%

numeric values and identifiers related to measurements or performance metrics

No Comments

No Known Activations