INDEX

Explanations

concepts related to mutation and data structure manipulation in programming

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

TERN

-0.17

licable

-0.15

 Trang

-0.15

unte

-0.14

unta

-0.14

ultipart

-0.14

OffsetTable

-0.14

itters

-0.14

PI

-0.13

usi

-0.13

POSITIVE LOGITS

ä¾¿

0.16

iller

0.15

 ConnectionState

0.15

/share

0.14

agers

0.14

 ownership

0.14

uario

0.14

Dak

0.13

Bib

0.13

 Fusion

0.13

Activations Density 0.045%

concepts related to mutation and data structure manipulation in programming

No Comments

No Known Activations