INDEX

Explanations

connections and relationships between characters

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

ãģĿãĤĮãģ¯

-0.15

 einf

-0.15

nor

-0.15

mis

-0.14

assis

-0.14

ace

-0.14

-qu

-0.14

 fing

-0.14

 Wash

-0.13

POSITIVE LOGITS

ugin

0.19

 sich

0.19

bette

0.18

AtA

0.17

 zich

0.16

yny

0.15

.wp

0.15

 Ø¨ØªÙĪØ§ÙĨ

0.15

à¸±à¸ģà¸Ķ

0.15

afx

0.15

Activations Density 0.091%

connections and relationships between characters

No Comments

No Known Activations