INDEX

Explanations

terms related to measurements, access, and secure connections

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

 Quar

-0.16

ãĥ¼ãĤ¹ãĥĪ

-0.16

è¨İ

-0.15

åł´

-0.14

 Tube

-0.14

CEF

-0.14

 tslib

-0.14

Kre

-0.14

 Canter

-0.14

POSITIVE LOGITS

0.16

oul

0.15

sm

0.15

Ð»Ð»

0.15

 Malik

0.15

occo

0.15

plain

0.15

roke

0.14

Activations Density 0.048%

terms related to measurements, access, and secure connections

No Comments

No Known Activations