INDEX

Explanations

verbs and actions related to detecting or identifying individuals and their abilities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

£½

-0.17

aise

-0.16

ollen

-0.15

elas

-0.14

 bekom

-0.14

ÙĬØ³

-0.14

deaux

-0.14

 portfolio

-0.14

zend

-0.14

 slim

-0.14

POSITIVE LOGITS

lyn

0.17

à¸±à¸Ļà¸¢

0.15

 Furn

0.14

.crm

0.14

Ð°Ð»ÐµÐ¶

0.14

umerator

0.14

voie

0.13

\views

0.13

Ø§Ø¨Ø±

0.13

jo

0.13

Activations Density 0.001%

verbs and actions related to detecting or identifying individuals and their abilities

No Comments

No Known Activations