INDEX

Explanations

technical jargon and specific terminology related to regulatory frameworks and programming

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

éĥİ

-0.16

raphics

-0.16

protocol

-0.15

ilters

-0.15

ahr

-0.15

åĲĪ

-0.14

stad

-0.14

ÑĢÐ°Ð´Ð¸

-0.13

licted

-0.13

unks

-0.13

POSITIVE LOGITS

atel

0.14

rello

0.14

ighet

0.14

0.13

oda

0.13

atha

0.13

 ìĿ´ìĥģ

0.13

 outr

0.13

 èĬ

0.13

Activations Density 0.308%

technical jargon and specific terminology related to regulatory frameworks and programming

No Comments

No Known Activations