INDEX

Explanations

terms related to evaluations of value and reality within philosophical or psychological contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

 prom

-0.15

 Flames

-0.14

rec

-0.14

ightly

-0.14

ellas

-0.14

 Gore

-0.14

 Victorian

-0.13

(',',$

-0.13

.lab

-0.13

 intr

-0.13

POSITIVE LOGITS

upo

0.17

Ì§

0.16

ãĥ¼ãĥŃ

0.16

Ø¨Ø§Ø²

0.15

ucs

0.15

ê³

0.15

aks

0.14

 Ashton

0.14

ÙĩØ±

0.14

olm

0.14

Activations Density 0.004%

terms related to evaluations of value and reality within philosophical or psychological contexts

No Comments

No Known Activations