INDEX

Explanations

instances of significant concepts in functional programming and related legal terminology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

-0.14

lington

-0.14

 mÃ¡t

-0.14

:[[

-0.14

jos

-0.14

sten

-0.14

unb

-0.14

enis

-0.14

-0.13

POSITIVE LOGITS

ĥģ

0.16

orks

0.15

mas

0.15

ems

0.14

strand

0.14

Close

0.14

ortion

0.13

alone

0.13

orig

0.13

.RESET

0.13

Activations Density 0.001%

instances of significant concepts in functional programming and related legal terminology

No Comments

No Known Activations