INDEX

Explanations

significant and impactful verbs or actions that indicate intent or emotion

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

adx

-0.16

agram

-0.16

vat

-0.16

ãĥ¬ãĥĥãĥĪ

-0.15

psy

-0.14

 ----------------------------------------------------------------------------------------------------------------

-0.14

/pm

-0.14

anske

-0.14

arel

-0.13

iges

-0.13

POSITIVE LOGITS

lero

0.17

esser

0.16

vla

0.16

áº¯n

0.15

å¼ı

0.15

 Recommended

0.14

utenberg

0.14

ãĥĳãĥ³

0.14

/ext

0.14

 fore

0.14

Activations Density 0.020%

significant and impactful verbs or actions that indicate intent or emotion

No Comments

No Known Activations