INDEX

Explanations

instances highlighting significant precedents or first-time occurrences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

egas

-0.16

á»ĳt

-0.15

 earlier

-0.15

arna

-0.15

crest

-0.14

áº¯t

-0.14

il

-0.14

ConverterFactory

-0.14

 Chamber

-0.13

ESIS

-0.13

POSITIVE LOGITS

-ever

0.17

 ever

0.16

_Tis

0.14

 appearance

0.13

ueblo

0.13

washer

0.13

.Endpoint

0.13

.scalablytyped

0.13

PyObject

0.13

wald

0.13

Activations Density 0.052%

instances highlighting significant precedents or first-time occurrences

No Comments

No Known Activations