INDEX

Explanations

references to specific numerical values and quantities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

ardy

-0.15

plib

-0.14

endregion

-0.14

ÐłÐ¾Ð·

-0.14

rosso

-0.14

ttp

-0.14

Reuse

-0.14

ignal

-0.14

ylie

-0.14

iler

-0.13

POSITIVE LOGITS

Alter

0.15

uncture

0.15

 Alter

0.15

achi

0.14

Lep

0.13

rome

0.13

 lean

0.13

earing

0.13

apon

0.13

pod

0.13

Activations Density 0.218%

references to specific numerical values and quantities

No Comments

No Known Activations