INDEX

Explanations

references to amounts or quantities in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Duty

-0.15

olson

-0.14

ä¼į

-0.14

 è©ķä¾¡

-0.14

.Logic

-0.13

.AnchorStyles

-0.13

enberg

-0.13

å±ĭ

-0.13

ISION

-0.13

aho

-0.13

POSITIVE LOGITS

 obviously

0.63

å½ĵçĦ¶

0.55

 course

0.54

 ÐºÐ¾Ð½ÐµÑĩÐ½Ð¾

0.53

 natÃ¼rlich

0.50

 samozÅĻejmÄĽ

0.48

course

0.46

 Obviously

0.44

 claro

0.44

 obvious

0.42

Activations Density 0.544%

references to amounts or quantities in various contexts

No Comments

No Known Activations