INDEX

Explanations

parameters in code, specifically for database queries

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

amba

-0.17

ChangedEventArgs

-0.15

olon

-0.15

ars

-0.14

ÐµÑĢÐ³

-0.14

oons

-0.14

yan

-0.14

/goto

-0.13

erse

-0.13

irket

-0.13

POSITIVE LOGITS

0.15

Indexed

0.14

ple

0.14

IVA

0.14

ETA

0.13

Ã¶h

0.13

REFIX

0.13

oleon

0.13

åįı

0.13

ØªÙĥ

0.13

Activations Density 0.009%

parameters in code, specifically for database queries

No Comments

No Known Activations