INDEX

Explanations

references to performance or execution in a programming context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

odu

-0.17

otron

-0.16

alist

-0.15

RuleContext

-0.15

estr

-0.15

 Muham

-0.14

hed

-0.14

.Annotations

-0.13

raph

-0.13

inf

-0.13

POSITIVE LOGITS

unden

0.17

Cong

0.16

kok

0.15

oref

0.15

 stakes

0.15

uren

0.14

 Cong

0.14

 Beds

0.14

tail

0.14

reich

0.14

Activations Density 0.138%

references to performance or execution in a programming context

No Comments

No Known Activations