INDEX

Explanations

occurrences of temporal or conjunctive phrases suggesting sequences or connections in actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

 indeed

-0.15

ages

-0.14

otti

-0.13

 moda

-0.13

è®

-0.13

 Barker

-0.13

inski

-0.13

elp

-0.13

arges

-0.13

.Servlet

-0.13

POSITIVE LOGITS

 Others

0.20

Others

0.20

others

0.20

 others

0.19

istrovstvÃŃ

0.17

 naopak

0.16

 smaller

0.16

 tháºŃm

0.15

 outlier

0.15

lÃ¡d

0.15

Activations Density 0.021%

occurrences of temporal or conjunctive phrases suggesting sequences or connections in actions

No Comments

No Known Activations