INDEX

Explanations

references to relatable human experiences and emotions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

 Witnesses

-0.15

Ð½Ð°Ð´

-0.15

Associated

-0.15

Ã¡ng

-0.14

Å¯Å¾

-0.14

 Witness

-0.14

_FA

-0.13

ÑĥÐ¿

-0.13

/runtime

-0.13

å§ĭ

-0.13

POSITIVE LOGITS

 relate

0.22

 universal

0.21

rel

0.20

ilha

0.20

 univers

0.20

universal

0.20

 applicable

0.19

 identification

0.19

 relating

0.19

 relates

0.18

Activations Density 0.175%

references to relatable human experiences and emotions

No Comments

No Known Activations