INDEX

Explanations

references to people and their roles or relationships 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 @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

 such

-0.18

such

-0.17

uru

-0.16

 SUCH

-0.16

è¿Ļä¸Ģ

-0.15

 addCriterion

-0.15

éĤ£ç§į

-0.15

its

-0.15

ardown

-0.14

POSITIVE LOGITS

 themselves

0.21

curity

0.18

ìłĢ

0.15

-ci

0.15

ificate

0.14

arest

0.14

 selves

0.14

ÙĪØ¯ÛĮ

0.14

bell

0.14

iones

0.14

Activations Density 0.130%

references to people and their roles or relationships in various contexts

No Comments

No Known Activations