INDEX

Explanations

content related to rules and regulations, particularly in legal or societal contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

empre

-0.14

(er

-0.13

ughter

-0.13

 erotik

-0.13

atts

-0.12

µľ

-0.12

emento

-0.12

ċ

-0.12

zm

-0.11

 taraf

-0.11

POSITIVE LOGITS

.Formatter

0.14

Ľå»º

0.14

.firebaseapp

0.13

ĶåĽŀ

0.13

@gmail

0.13

ãĥ¼ãĥ«

0.13

ÑĢÑĸÐ´

0.13

sic

0.13

sembl

0.13

.newaxis

0.13

Activations Density 4.218%

content related to rules and regulations, particularly in legal or societal contexts

No Comments

No Known Activations