INDEX

Explanations

encoded data or specific patterns within a data format

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

owi

-0.17

è¦§

-0.16

mpar

-0.16

ovel

-0.15

ndef

-0.15

ysi

-0.15

Marsh

-0.15

endet

-0.15

oog

-0.15

aginator

-0.14

POSITIVE LOGITS

 clin

0.15

 Vera

0.15

ãĥ¼ãĥĦ

0.15

Ð¾ÐºÐ¾Ð½

0.14

 Vere

0.13

eyJ

0.13

 ç´

0.13

VERSE

0.13

 Bang

0.13

 strict

0.13

Activations Density 0.001%

encoded data or specific patterns within a data format

No Comments

No Known Activations